From 5d08ad86ae45478db3742fef51c7c0ae38f30e34 Mon Sep 17 00:00:00 2001
From: Claudio Atzori <claudio.atzori@isti.cnr.it>
Date: Thu, 29 Jul 2021 13:03:16 +0200
Subject: [PATCH] [raw_all] patching relation identifier phase to be run at the
 end, i.e. includes also claimed relations

---
 .../oa/graph/raw_all/oozie_app/workflow.xml   | 75 +++++++++----------
 1 file changed, 37 insertions(+), 38 deletions(-)

diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_all/oozie_app/workflow.xml b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_all/oozie_app/workflow.xml
index e7320de3b..321ca4090 100644
--- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_all/oozie_app/workflow.xml
+++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_all/oozie_app/workflow.xml
@@ -548,42 +548,7 @@
         <error to="Kill"/>
     </action>
 
-    <join name="wait_graphs" to="patchRelations"/>
-
-    <decision name="decisionPatchRelations">
-        <switch>
-            <case to="patchRelations">
-                ${(shouldPatchRelations eq "true") and
-                (fs:exists(concat(concat(wf:conf('nameNode'),'/'),wf:conf('idMappingPath'))) eq "true")}
-            </case>
-            <default to="fork_merge_claims"/>
-        </switch>
-    </decision>
-
-    <action name="patchRelations">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>PatchRelations</name>
-            <class>eu.dnetlib.dhp.oa.graph.raw.PatchRelationsApplication</class>
-            <jar>dhp-graph-mapper-${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}${spark2EventLogDir}
-                --conf spark.sql.shuffle.partitions=7680
-            </spark-opts>
-            <arg>--graphBasePath</arg><arg>${workingDir}/graph_raw</arg>
-            <arg>--workingDir</arg><arg>${workingDir}/patch_relations</arg>
-            <arg>--idMappingPath</arg><arg>${idMappingPath}</arg>
-        </spark>
-        <ok to="fork_merge_claims"/>
-        <error to="Kill"/>
-    </action>
+    <join name="wait_graphs" to="fork_merge_claims"/>
 
     <fork name="fork_merge_claims">
         <path start="merge_claims_publication"/>
@@ -596,7 +561,6 @@
         <path start="merge_claims_relation"/>
     </fork>
 
-
     <action name="merge_claims_publication">
         <spark xmlns="uri:oozie:spark-action:0.2">
             <master>yarn</master>
@@ -805,7 +769,42 @@
         <error to="Kill"/>
     </action>
 
-    <join name="wait_merge" to="End"/>
+    <join name="wait_merge" to="decisionPatchRelations"/>
+
+    <decision name="decisionPatchRelations">
+        <switch>
+            <case to="patchRelations">
+                ${(shouldPatchRelations eq "true") and
+                (fs:exists(concat(concat(wf:conf('nameNode'),'/'),wf:conf('idMappingPath'))) eq "true")}
+            </case>
+            <default to="End"/>
+        </switch>
+    </decision>
+
+    <action name="patchRelations">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>PatchRelations</name>
+            <class>eu.dnetlib.dhp.oa.graph.raw.PatchRelationsApplication</class>
+            <jar>dhp-graph-mapper-${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}${spark2EventLogDir}
+                --conf spark.sql.shuffle.partitions=7680
+            </spark-opts>
+            <arg>--graphBasePath</arg><arg>${graphOutputPath}</arg>
+            <arg>--workingDir</arg><arg>${workingDir}/patch_relations</arg>
+            <arg>--idMappingPath</arg><arg>${idMappingPath}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
 
     <end name="End"/>
 </workflow-app>
\ No newline at end of file