From 7473093c84df9c1f61fac9e1537e6ec4b41ad904 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 10 Feb 2023 15:34:52 +0100 Subject: [PATCH] [FoS] changed the default separator from comma to tab to solve the issue in subject value split --- .../main/java/eu/dnetlib/dhp/actionmanager/Constants.java | 1 + .../createunresolvedentities/GetFOSSparkJob.java | 7 +++---- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java index aa25ca633..6167182a8 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java @@ -21,6 +21,7 @@ public class Constants { public static final String DOI_CLASSNAME = "Digital Object Identifier"; public static final String DEFAULT_DELIMITER = ","; + public static final String DEFAULT_FOS_DELIMITER = "\t"; public static final String UPDATE_DATA_INFO_TYPE = "update"; public static final String UPDATE_SUBJECT_FOS_CLASS_ID = "subject:fos"; diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetFOSSparkJob.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetFOSSparkJob.java index 75fe42e90..c98f1b05a 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetFOSSparkJob.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetFOSSparkJob.java @@ -1,7 +1,7 @@ package eu.dnetlib.dhp.actionmanager.createunresolvedentities; -import static eu.dnetlib.dhp.actionmanager.Constants.DEFAULT_DELIMITER; +import static eu.dnetlib.dhp.actionmanager.Constants.DEFAULT_FOS_DELIMITER; import static eu.dnetlib.dhp.actionmanager.Constants.isSparkSessionManaged; import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; @@ -9,8 +9,7 @@ import java.io.Serializable; import java.util.Optional; import org.apache.commons.io.IOUtils; -import org.apache.hadoop.conf.Configuration; -import org.apache.hadoop.fs.FileSystem; + import org.apache.spark.SparkConf; import org.apache.spark.api.java.function.MapFunction; import org.apache.spark.sql.*; @@ -49,7 +48,7 @@ public class GetFOSSparkJob implements Serializable { final String delimiter = Optional .ofNullable(parser.get("delimiter")) - .orElse(DEFAULT_DELIMITER); + .orElse(DEFAULT_FOS_DELIMITER); SparkConf sconf = new SparkConf(); runWithSparkSession(