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

Generate "merged" dedup id relations also for records that are filtered out by the cut parameters

This commit is contained in:
Giambattista Bloisi 2023-12-14 11:51:02 +01:00 committed by Giambattista Bloisi
parent 1287315ffb
commit 831cc1fdde
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java
View File

@ -213,7 +213,6 @@ public class SparkCreateMergeRels extends AbstractSparkAction {
.join(pivotingData, JavaConversions.asScalaBuffer(Collections.singletonList("id")), "left")
.withColumn("pivot", functions.first("id").over(w))
.withColumn("position", functions.row_number().over(w))
.filter(cut > 0 ? col("position").lt(lit(cut)) : lit(true)) // apply cut after choosing pivot
.flatMap(
(FlatMapFunction<Row, Tuple3<String, String, String>>) (Row r) -> {
String id = r.getAs("id");
@ -249,7 +248,9 @@ public class SparkCreateMergeRels extends AbstractSparkAction {
}
// add merge relations
res.add(new Tuple3<>(id, pivotDedupId, pivot));
if (cut <=0 || r.<Integer>getAs("position") <= cut) {
res.add(new Tuple3<>(id, pivotDedupId, pivot));
}
return res.iterator();
}, Encoders.tuple(Encoders.STRING(), Encoders.STRING(), Encoders.STRING()))