From e80f80ca9390c8d6636c8c358b80d04f60dc227b Mon Sep 17 00:00:00 2001
From: "miriam.baglioni" <miriam.baglioni@isti.cnr.it>
Date: Mon, 2 Mar 2020 17:03:31 +0100
Subject: [PATCH] properties and workflow for new propagation

---
 .../input_communitytoresult_parameters.json   | 21 +++++++
 .../oozie_app/config-default.xml              | 18 ++++++
 .../oozie_app/workflow.xml                    | 55 +++++++++++++++++++
 3 files changed, 94 insertions(+)
 create mode 100644 dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json
 create mode 100644 dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml
 create mode 100644 dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml

diff --git a/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json b/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json
new file mode 100644
index 0000000000..ec2549d049
--- /dev/null
+++ b/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json
@@ -0,0 +1,21 @@
+[
+  {
+    "paramName":"mt",
+    "paramLongName":"master",
+    "paramDescription": "should be local or yarn",
+    "paramRequired": true
+  },
+  {
+    "paramName":"s",
+    "paramLongName":"sourcePath",
+    "paramDescription": "the path of the sequencial file to read",
+    "paramRequired": true
+  },
+
+  {
+    "paramName":"ocm",
+    "paramLongName":"organizationtoresultcommunitymap",
+    "paramDescription": "the map in json format assocaition the organization original id with the list of communities",
+    "paramRequired": true
+  }
+]
\ No newline at end of file
diff --git a/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml b/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml
new file mode 100644
index 0000000000..2e0ed9aeea
--- /dev/null
+++ b/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml
@@ -0,0 +1,18 @@
+<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>
+</configuration>
\ No newline at end of file
diff --git a/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml b/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml
new file mode 100644
index 0000000000..cb85030d8f
--- /dev/null
+++ b/dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml
@@ -0,0 +1,55 @@
+<workflow-app name="community_to_result_propagation" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>sourcePath</name>
+            <description>the source path</description>
+        </property>
+        <property>
+            <name>organizationtoresultcommunitymap</name>
+            <description>organization community map</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>
+    </parameters>
+
+    <start to="CommunityToResultFromOrganizationPropagation"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+    <action name="CommunityToResultFromOrganizationPropagation">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <master>yarn-cluster</master>
+            <mode>cluster</mode>
+            <name>ProjectToResultPropagation</name>
+            <class>eu.dnetlib.dhp.projecttoresult.SparkResultToProjectThroughSemRelJob</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>--executor-memory ${sparkExecutorMemory}
+                --executor-cores ${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
+                --conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
+            </spark-opts>
+            <arg>-mt</arg> <arg>yarn-cluster</arg>
+            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
+            <arg>--organizationtoresultcommunitymap</arg><arg>${organizationtoresultcommunitymap}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+    <end name="End"/>
+</workflow-app>
\ No newline at end of file