From dcff9cecdf2267b2689bc71dbe67a15bb15b7f34 Mon Sep 17 00:00:00 2001
From: miconis <m.debonis991@gmail.com>
Date: Mon, 12 Apr 2021 15:55:27 +0200
Subject: [PATCH] bug fix: ids in self mergerels are not marked
 deletedbyinference=true

---
 .../main/java/eu/dnetlib/dhp/oa/dedup/SparkUpdateEntity.java    | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkUpdateEntity.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkUpdateEntity.java
index 779fb91d6..b65822635 100644
--- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkUpdateEntity.java
+++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkUpdateEntity.java
@@ -13,6 +13,7 @@ import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.JavaPairRDD;
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.MapFunction;
 import org.apache.spark.api.java.function.PairFunction;
 import org.apache.spark.sql.Dataset;
 import org.apache.spark.sql.Encoders;
@@ -91,6 +92,7 @@ public class SparkUpdateEntity extends AbstractSparkAction {
 
 						final JavaPairRDD<String, String> mergedIds = rel
 							.where("relClass == 'merges'")
+							.where("source != target")
 							.select(rel.col("target"))
 							.distinct()
 							.toJavaRDD()