From 4f2a61e10fc5b6983f6f637120eef0c67f38f73d Mon Sep 17 00:00:00 2001 From: Giambattista Bloisi Date: Wed, 29 May 2024 23:05:20 +0200 Subject: [PATCH] Change the selection criteria for the pivot record of a group so that by best pid type becomes the first criteria. This will have the effect to slowly converge to records having DOI pid --- .../main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java index f73ff92ec..0ff40f6f8 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java +++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java @@ -203,8 +203,8 @@ public class SparkCreateMergeRels extends AbstractSparkAction { WindowSpec w = Window .partitionBy("groupId") .orderBy( - col("lastUsage").desc_nulls_last(), col("pidType").asc_nulls_last(), + col("lastUsage").desc_nulls_last(), col("collectedfrom").desc_nulls_last(), col("date").asc_nulls_last(), col("id").asc_nulls_last());