input parameters and workflow for new implementation of propagation of orcid to result from semrel and preparation phases

dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json

@@ -1,32 +1,38 @@
 [
-  {
-    "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":"as",
-    "paramLongName":"allowedsemrels",
-    "paramDescription": "the allowed sematinc relations for propagation",
-    "paramRequired": true
-  },
-  {
-    "paramName":"wu",
-    "paramLongName":"writeUpdate",
-    "paramDescription": "true if the update must be writte. No double check if information is already present",
-    "paramRequired": true
-  },
   {
     "paramName":"sg",
     "paramLongName":"saveGraph",
     "paramDescription": "true if the new version of the graph must be saved",
     "paramRequired": true
+  },
+  {
+    "paramName":"h",
+    "paramLongName":"hive_metastore_uris",
+    "paramDescription": "the hive metastore uris",
+    "paramRequired": true
+  },
+  {
+    "paramName": "out",
+    "paramLongName": "outputPath",
+    "paramDescription": "the path used to store temporary output files",
+    "paramRequired": true
+  },
+  {
+    "paramName": "ssm",
+    "paramLongName": "isSparkSessionManaged",
+    "paramDescription": "true if the spark session is managed, false otherwise",
+    "paramRequired": false
+  },
+  {
+    "paramName":"tn",
+    "paramLongName":"resultTableName",
+    "paramDescription": "the name of the result table we are currently working on",
+    "paramRequired": true
   }
 ]

dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json

@@ -1,10 +1,4 @@
 [
-  {
-    "paramName":"mt",
-    "paramLongName":"master",
-    "paramDescription": "should be local or yarn",
-    "paramRequired": true
-  },
   {
     "paramName":"s",
     "paramLongName":"sourcePath",
@@ -18,15 +12,27 @@
     "paramRequired": true
   },
   {
-    "paramName":"wu",
-    "paramLongName":"writeUpdate",
-    "paramDescription": "true if the update must be writte. No double check if information is already present",
+    "paramName":"h",
+    "paramLongName":"hive_metastore_uris",
+    "paramDescription": "the hive metastore uris",
     "paramRequired": true
   },
   {
-    "paramName":"sg",
-    "paramLongName":"saveGraph",
-    "paramDescription": "true if the new version of the graph must be saved",
+    "paramName": "out",
+    "paramLongName": "outputPath",
+    "paramDescription": "the path used to store temporary output files",
+    "paramRequired": true
+  },
+  {
+    "paramName": "ssm",
+    "paramLongName": "isSparkSessionManaged",
+    "paramDescription": "true if the spark session is managed, false otherwise",
+    "paramRequired": false
+  },
+  {
+    "paramName":"tn",
+    "paramLongName":"resultTableName",
+    "paramDescription": "the name of the result table we are currently working on",
     "paramRequired": true
   }
 ]

dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json

@@ -5,18 +5,6 @@
     "paramDescription": "the path of the sequencial file to read",
     "paramRequired": true
   },
-  {
-    "paramName":"as",
-    "paramLongName":"allowedsemrels",
-    "paramDescription": "the allowed sematinc relations for propagation",
-    "paramRequired": true
-  },
-  {
-    "paramName":"h",
-    "paramLongName":"hive_metastore_uris",
-    "paramDescription": "the hive metastore uris",
-    "paramRequired": true
-  },
   {
     "paramName": "out",
     "paramLongName": "outputPath",
@@ -28,11 +16,5 @@
     "paramLongName": "isSparkSessionManaged",
     "paramDescription": "true if the spark session is managed, false otherwise",
     "paramRequired": false
-  },
-  {
-    "paramName":"tn",
-    "paramLongName":"resultTableName",
-    "paramDescription": "the name of the result table we are currently working on",
-    "paramRequired": true
   }
 ]

dhp-workflows/dhp-propagation/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/workflow.xml

@@ -8,18 +8,6 @@
         <name>allowedsemrels</name>
         <description>the semantic relationships allowed for propagation</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>writeUpdate</name>
         <description>writes the information found for the update. No double check done if the information is already present</description>
@@ -30,12 +18,133 @@
     </property>
 </parameters>
 
-<start to="OrcidToResultFromSemRelPropagation"/>
+<start to="fork_prepare_assoc_step1"/>
 
 <kill name="Kill">
     <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
 </kill>
 
+    <fork name="fork_prepare_assoc_step1">
+        <path start="join_prepare_publication"/>
+        <path start="join_prepare_dataset"/>
+        <path start="join_prepare_otherresearchproduct"/>
+        <path start="join_prepare_software"/>
+    </fork>
+
+    <action name="join_prepare_publication">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
+            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
+        </spark>
+        <ok to="wait"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="join_prepare_dataset">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
+            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
+        </spark>
+        <ok to="wait"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="join_prepare_otherresearchproduct">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
+            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
+        </spark>
+        <ok to="wait"/>
+        <error to="Kill"/>
+    </action>
+
+    <action name="join_prepare_software">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
+            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+
+
 <action name="OrcidToResultFromSemRelPropagation">
     <spark xmlns="uri:oozie:spark-action:0.2">
         <job-tracker>${jobTracker}</job-tracker>
@@ -67,5 +176,145 @@
     <error to="Kill"/>
 </action>
 
+    <join name="wait" to="prepare_assoc_step2"/>
+
+    <action name="prepare_assoc_step2">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep2</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
+        </spark>
+<!--        <ok to="fork-join-exec-propagation"/>-->
+        <ok to="End"/>
+        <error to="Kill"/>
+
+    </action>
+    <fork name="fork-join-exec-propagation">
+        <path start="join_propagate_publication"/>
+        <path start="join_propagate_dataset"/>
+        <path start="join_propagate_otherresearchproduct"/>
+        <path start="join_propagate_software"/>
+    </fork>
+
+    <action name="join_propagate_publication">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob3</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
+            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/publication</arg>
+        </spark>
+        <ok to="wait2"/>
+        <error to="Kill"/>
+    </action>
+    <action name="join_propagate_dataset">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob3</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --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.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
+            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/dataset</arg>
+        </spark>
+        <ok to="wait2"/>
+        <error to="Kill"/>
+    </action>
+    <action name="join_propagate_otherresearchproduct">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob3</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+                --conf spark.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
+            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/otherresearchproduct</arg>
+        </spark>
+        <ok to="wait2"/>
+        <error to="Kill"/>
+    </action>
+    <action name="join_propagate_software">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>ORCIDpropagationFromSemRel</name>
+            <class>eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob3</class>
+            <jar>dhp-propagation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-cores=${sparkExecutorCores}
+                --executor-memory=${sparkExecutorMemory}
+                --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.dynamicAllocation.enabled=true
+                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
+            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
+            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
+            <arg>--outputPath</arg><arg>${workingDir}/software</arg>
+        </spark>
+        <ok to="wait2"/>
+        <error to="Kill"/>
+    </action>
+    <join name="wait2" to="End"/>
 <end name="End"/>
 </workflow-app>