From 0e44b037a52558e20bbe418a5d313fc7fd8e966f Mon Sep 17 00:00:00 2001
From: Giambattista Bloisi <giambattista.bloisi@openaire.eu>
Date: Tue, 17 Oct 2023 07:54:01 +0200
Subject: [PATCH] FIX: GroupEntitiesSparkJob deletes whole graph outputPath
 instead of its temporary folder

---
 .../java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java b/dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java
index 99981bf6a..f5c8eea19 100644
--- a/dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java
+++ b/dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java
@@ -71,7 +71,7 @@ public class GroupEntitiesSparkJob {
 			conf,
 			isSparkSessionManaged,
 			spark -> {
-				HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration());
+				HdfsSupport.remove(checkpointPath, spark.sparkContext().hadoopConfiguration());
 				groupEntities(spark, graphInputPath, checkpointPath, outputPath, filterInvisible);
 			});
 	}