From 3dd5701948404355f3f427b135277c3ba4ca2795 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Tue, 29 Jun 2021 12:10:27 +0200 Subject: [PATCH] added the normalization step to the doi from crossref --- .../java/eu/dnetlib/doiboost/crossref/CrossrefDataset.scala | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/CrossrefDataset.scala b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/CrossrefDataset.scala index 235305fb8..e43fdcdfb 100644 --- a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/CrossrefDataset.scala +++ b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/CrossrefDataset.scala @@ -1,6 +1,7 @@ package eu.dnetlib.doiboost.crossref import eu.dnetlib.dhp.application.ArgumentApplicationParser +import eu.dnetlib.doiboost.DoiBoostMappingUtil import org.apache.commons.io.IOUtils import org.apache.hadoop.io.{IntWritable, Text} import org.apache.spark.SparkConf @@ -22,7 +23,7 @@ object CrossrefDataset { lazy val json: json4s.JValue = parse(input) val ts:Long = (json \ "indexed" \ "timestamp").extract[Long] val doi:String = (json \ "DOI").extract[String] - CrossrefDT(doi, input, ts) + CrossrefDT(DoiBoostMappingUtil.normalizeDoi(doi), input, ts) }