Merge branch 'stable_ids' of https://code-repo.d4science.org/D-Net/dnet-hadoop into stable_ids

2021-04-12 17:32:09 +02:00 · 2021-04-12 17:32:09 +02:00 · 72dcadd8e6
parent 902d05f548 d442e25cbc
commit 72dcadd8e6
1 changed files with 1 additions and 0 deletions
--- 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
@ -91,6 +91,7 @@ public class SparkUpdateEntity extends AbstractSparkAction {

 						final JavaPairRDD<String, String> mergedIds = rel
 							.where("relClass == 'merges'")
+							.where("source != target")
 							.select(rel.col("target"))
 							.distinct()
 							.toJavaRDD()