From 5fd0e610bf1cb1cd6f8e80e047602fba2703ddce Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Thu, 25 Nov 2021 12:10:45 +0100 Subject: [PATCH] [DOIBOOST Process] fix filtering to filter results with non null id --- .../src/main/java/eu/dnetlib/doiboost/mag/SparkProcessMAG.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/mag/SparkProcessMAG.scala b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/mag/SparkProcessMAG.scala index 016279787..0ea4b66a4 100644 --- a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/mag/SparkProcessMAG.scala +++ b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/mag/SparkProcessMAG.scala @@ -146,7 +146,7 @@ object SparkProcessMAG { .save(s"$workingPath/mag_publication") spark.read.load(s"$workingPath/mag_publication").as[Publication] - .filter(p => p.getId == null) + .filter(p => p.getId != null) .groupByKey(p => p.getId) .reduceGroups((a:Publication, b:Publication) => ConversionUtil.mergePublication(a,b)) .map(_._2)