mergin with branch beta

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkConvertRDDtoDataset.scala

@@ -59,7 +59,7 @@ object SparkConvertRDDtoDataset {
     log.info("Converting Relation")
 
 
-    val rddRelation =spark.sparkContext.textFile(s"$sourcePath/relation").map(s => mapper.readValue(s, classOf[Relation]))
+    val rddRelation =spark.sparkContext.textFile(s"$sourcePath/relation").map(s => mapper.readValue(s, classOf[Relation])).filter(r=> r.getSource.startsWith("50") && r.getTarget.startsWith("50"))
     spark.createDataset(rddRelation).as[Relation].write.mode(SaveMode.Overwrite).save(s"$relPath")
 
 

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkCreateScholix.scala

@@ -51,10 +51,14 @@ object SparkCreateScholix {
 
     relationDS.joinWith(summaryDS, relationDS("_1").equalTo(summaryDS("_1")), "left")
       .map { input: ((String, Relation), (String, ScholixSummary)) =>
+        if (input._1!= null && input._2!= null) {
           val rel: Relation = input._1._2
           val source: ScholixSummary = input._2._2
           (rel.getTarget, ScholixUtils.scholixFromSource(rel, source))
+        }
+        else  null
       }(Encoders.tuple(Encoders.STRING, scholixEncoder))
+      .filter(r => r!= null)
       .write.mode(SaveMode.Overwrite).save(s"$targetPath/scholix_from_source")
 
     val scholixSource: Dataset[(String, Scholix)] = spark.read.load(s"$targetPath/scholix_from_source").as[(String, Scholix)](Encoders.tuple(Encoders.STRING, scholixEncoder))

dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/scholix/ScholixUtils.scala

@@ -289,7 +289,7 @@ object ScholixUtils {
     if (r.getInstance() == null || r.getInstance().isEmpty)
       return List()
     r.getInstance().asScala.filter(i => i.getUrl!= null && !i.getUrl.isEmpty)
-
+      .filter(i => i.getPid!= null && i.getUrl != null)
       .flatMap(i => findURLForPID(i.getPid.asScala.toList, i.getUrl.asScala.toList))
       .map(i => new ScholixIdentifier(i._1.getValue, i._1.getQualifier.getClassid, i._2)).distinct.toList
   }

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/finalGraph/oozie_app/workflow.xml

@@ -54,7 +54,7 @@
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.shuffle.partitions=5000
+                --conf spark.sql.shuffle.partitions=20000
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
@@ -79,7 +79,7 @@
                 --executor-cores=${sparkExecutorCores}
                 --driver-memory=${sparkDriverMemory}
                 --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.shuffle.partitions=6000
+                --conf spark.sql.shuffle.partitions=20000
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                 --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}

dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step11.sql

@@ -65,7 +65,7 @@ FROM ${stats_db_name}.project_tmp p
 UPDATE ${stats_db_name}.publication_tmp
 SET delayed = 'yes'
 WHERE publication_tmp.id IN (SELECT distinct r.id
-                             FROM stats_wf_db_obs.result r,
+                             FROM ${stats_db_name}.result r,
                                   ${stats_db_name}.project_results pr,
                                   ${stats_db_name}.project_tmp p
                              WHERE r.id = pr.result
@@ -75,7 +75,7 @@ WHERE publication_tmp.id IN (SELECT distinct r.id
 UPDATE ${stats_db_name}.dataset_tmp
 SET delayed = 'yes'
 WHERE dataset_tmp.id IN (SELECT distinct r.id
-                         FROM stats_wf_db_obs.result r,
+                         FROM ${stats_db_name}.result r,
                               ${stats_db_name}.project_results pr,
                               ${stats_db_name}.project_tmp p
                          WHERE r.id = pr.result