antonis.lempesis
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 1
Code Issues Pull Requests Projects Releases Wiki Activity

FIX: GroupEntitiesSparkJob deletes whole graph outputPath instead of its temporary folder

This commit is contained in:
Giambattista Bloisi 2023-10-17 07:54:01 +02:00
parent 6cf64d5d8b
commit 0e44b037a5
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/GroupEntitiesSparkJob.java
View File

@ -71,7 +71,7 @@ public class GroupEntitiesSparkJob {
conf, conf,
isSparkSessionManaged, isSparkSessionManaged,
spark -> { spark -> {
HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration()); HdfsSupport.remove(checkpointPath, spark.sparkContext().hadoopConfiguration());
groupEntities(spark, graphInputPath, checkpointPath, outputPath, filterInvisible); groupEntities(spark, graphInputPath, checkpointPath, outputPath, filterInvisible);
}); });
} }