forked from D-Net/dnet-hadoop
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
This commit is contained in:
parent
3d9ddaa23a
commit
13f6506ce5
|
@ -203,8 +203,8 @@ public class SparkCreateMergeRels extends AbstractSparkAction {
|
||||||
WindowSpec w = Window
|
WindowSpec w = Window
|
||||||
.partitionBy("groupId")
|
.partitionBy("groupId")
|
||||||
.orderBy(
|
.orderBy(
|
||||||
col("lastUsage").desc_nulls_last(),
|
|
||||||
col("pidType").asc_nulls_last(),
|
col("pidType").asc_nulls_last(),
|
||||||
|
col("lastUsage").desc_nulls_last(),
|
||||||
col("collectedfrom").desc_nulls_last(),
|
col("collectedfrom").desc_nulls_last(),
|
||||||
col("date").asc_nulls_last(),
|
col("date").asc_nulls_last(),
|
||||||
col("id").asc_nulls_last());
|
col("id").asc_nulls_last());
|
||||||
|
|
Loading…
Reference in New Issue