D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

patch relations job: removed non necessary logging

This commit is contained in:
Claudio Atzori 2024-10-30 07:35:30 +01:00
parent 69aee609ef
commit 323c76eafc
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/PatchRelationsApplication.java
View File

@ -80,9 +80,6 @@ public class PatchRelationsApplication {
final Dataset<Relation> rels = readPath(spark, relationPath, Relation.class); final Dataset<Relation> rels = readPath(spark, relationPath, Relation.class);
final Dataset<RelationIdMapping> idMapping = readPath(spark, idMappingPath, RelationIdMapping.class); final Dataset<RelationIdMapping> idMapping = readPath(spark, idMappingPath, RelationIdMapping.class);
log.info("relations: {}", rels.count());
log.info("idMapping: {}", idMapping.count());
final Dataset<Relation> bySource = rels final Dataset<Relation> bySource = rels
.joinWith(idMapping, rels.col("source").equalTo(idMapping.col("oldId")), "left") .joinWith(idMapping, rels.col("source").equalTo(idMapping.col("oldId")), "left")
.map((MapFunction<Tuple2<Relation, RelationIdMapping>, Relation>) t -> { .map((MapFunction<Tuple2<Relation, RelationIdMapping>, Relation>) t -> {