From 8e7ef79ce09d41d57d9d70f90875563bd2799e40 Mon Sep 17 00:00:00 2001
From: Claudio Atzori <claudio.atzori@isti.cnr.it>
Date: Mon, 5 Aug 2024 12:13:48 +0200
Subject: [PATCH] [bip affiliations] considers only DOI based records

---
 .../bipaffiliations/PrepareAffiliationRelations.java           | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java
index 8f911e980..98915bdc5 100644
--- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java
+++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java
@@ -129,7 +129,8 @@ public class PrepareAffiliationRelations implements Serializable {
 		Dataset<Row> df = spark
 			.read()
 			.schema("`DOI` STRING, `Matchings` ARRAY<STRUCT<`RORid`:STRING,`Confidence`:DOUBLE>>")
-			.json(inputPath);
+			.json(inputPath)
+			.where("DOI is not null");
 
 		// unroll nested arrays
 		df = df