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

[FoS] changed the default separator from comma to tab to solve the issue in subject value split

This commit is contained in:
Miriam Baglioni 2023-02-10 15:34:52 +01:00
parent 5f0906be60
commit 7473093c84
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/Constants.java
View File

@ -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";

7
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/GetFOSSparkJob.java
View File

@ -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(