From 4eba14a80e25d17cd476cc1f0ffe420654b50726 Mon Sep 17 00:00:00 2001
From: Serafeim Chatzopoulos <s.chatzopoulos@gmail.com>
Date: Thu, 6 Jul 2023 21:07:50 +0300
Subject: [PATCH] Add oozie workflow

---
 .../oozie_app/config-default.xml              |  30 +++++
 .../bipaffiliations/oozie_app/workflow.xml    | 108 ++++++++++++++++++
 2 files changed, 138 insertions(+)
 create mode 100644 dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/config-default.xml
 create mode 100644 dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml

diff --git a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/config-default.xml b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/config-default.xml
new file mode 100644
index 000000000..d262cb6e0
--- /dev/null
+++ b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/config-default.xml
@@ -0,0 +1,30 @@
+<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>hiveMetastoreUris</name>
+        <value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
+    </property>
+    <property>
+        <name>hiveJdbcUrl</name>
+        <value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000</value>
+    </property>
+    <property>
+        <name>hiveDbName</name>
+        <value>openaire</value>
+    </property>
+    <property>
+        <name>oozie.launcher.mapreduce.user.classpath.first</name>
+        <value>true</value>
+    </property>
+</configuration>
diff --git a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml
new file mode 100644
index 000000000..7c44bb7eb
--- /dev/null
+++ b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml
@@ -0,0 +1,108 @@
+<workflow-app name="BipFinderScore" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+
+        <property>
+            <name>inputPath</name>
+            <description>the path where to find the inferred affiliation relations</description>
+        </property>
+        <property>
+            <name>outputPath</name>
+            <description>the path where to store the actionset</description>
+        </property>
+        <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>
+        <property>
+            <name>oozieActionShareLibForSpark2</name>
+            <description>oozie action sharelib for spark 2.*</description>
+        </property>
+        <property>
+            <name>spark2ExtraListeners</name>
+            <value>com.cloudera.spark.lineage.NavigatorAppListener</value>
+            <description>spark 2.* extra listeners classname</description>
+        </property>
+        <property>
+            <name>spark2SqlQueryExecutionListeners</name>
+            <value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
+            <description>spark 2.* sql query execution listeners classname</description>
+        </property>
+        <property>
+            <name>spark2YarnHistoryServerAddress</name>
+            <description>spark 2.* yarn history server address</description>
+        </property>
+        <property>
+            <name>spark2EventLogDir</name>
+            <description>spark 2.* event log dir location</description>
+        </property>
+    </parameters>
+
+    <global>
+        <job-tracker>${jobTracker}</job-tracker>
+        <name-node>${nameNode}</name-node>
+        <configuration>
+            <property>
+                <name>mapreduce.job.queuename</name>
+                <value>${queueName}</value>
+            </property>
+            <property>
+                <name>oozie.launcher.mapred.job.queue.name</name>
+                <value>${oozieLauncherQueueName}</value>
+            </property>
+            <property>
+                <name>oozie.action.sharelib.for.spark</name>
+                <value>${oozieActionShareLibForSpark2}</value>
+            </property>
+
+        </configuration>
+    </global>
+    <start to="deleteoutputpath"/>
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+    <action name="deleteoutputpath">
+        <fs>
+            <delete path="${outputPath}"/>
+            <mkdir path="${outputPath}"/>
+            <delete path="${workingDir}"/>
+            <mkdir path="${workingDir}"/>
+        </fs>
+        <ok to="atomicactions"/>
+        <error to="Kill"/>
+    </action>
+
+
+    <action name="atomicactions">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Produces the atomic action with the inferred by BIP! affiliation relations from Crossref</name>
+            <class>eu.dnetlib.dhp.actionmanager.bipaffiliations.PrepareAffiliationRelations/class>
+            <jar>dhp-aggregation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${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}${spark2EventLogDir}
+                --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
+            </spark-opts>
+            <arg>--inputPath</arg><arg>${inputPath}</arg>
+            <arg>--outputPath</arg><arg>${outputPath}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+    <end name="End"/>
+</workflow-app>
\ No newline at end of file