antonis.lempesis
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 1
Code Issues Pull Requests Projects Releases Wiki Activity

[DUMP DELTA PROJECTS] refactoring

This commit is contained in:
Miriam Baglioni 2022-06-27 18:07:58 +02:00
parent 1d1fe3b151
commit 71744a1f52
1 changed files with 60 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/projectssubset/ProjectsSubsetSparkJob.java
View File

@ -1,28 +1,27 @@
package eu.dnetlib.dhp.oa.graph.dump.projectssubset; package eu.dnetlib.dhp.oa.graph.dump.projectssubset;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable; import java.io.Serializable;
import java.util.List;
import java.util.Objects; import java.util.Objects;
import java.util.Optional; import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.MapFunction; import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset; import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders; import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode; import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession; import org.apache.spark.sql.SparkSession;
import org.jetbrains.annotations.NotNull;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.graph.dump.Utils; import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.schema.dump.oaf.community.Funder;
import eu.dnetlib.dhp.schema.dump.oaf.graph.Project; import eu.dnetlib.dhp.schema.dump.oaf.graph.Project;
import scala.Tuple2; import scala.Tuple2;
public class ProjectsSubsetSparkJob implements Serializable { public class ProjectsSubsetSparkJob implements Serializable {
private static final Logger log = LoggerFactory.getLogger(ProjectsSubsetSparkJob.class); private static final Logger log = LoggerFactory.getLogger(ProjectsSubsetSparkJob.class);
public static void main(String[] args) throws Exception { public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils String jsonConfiguration = IOUtils
.toString( .toString(
@ -51,10 +50,10 @@ public class ProjectsSubsetSparkJob implements Serializable {
getNewProjectList(spark, inputPath, outputPath, projectListPath); getNewProjectList(spark, inputPath, outputPath, projectListPath);
}); });
} }
private static void getNewProjectList(SparkSession spark, String inputPath, String outputPath, private static void getNewProjectList(SparkSession spark, String inputPath, String outputPath,
String projectListPath) { String projectListPath) {
Dataset<String> projectList = spark.read().textFile(projectListPath); Dataset<String> projectList = spark.read().textFile(projectListPath);
// projectList.show(false);
Dataset<Project> projects; Dataset<Project> projects;
projects = Utils.readPath(spark, inputPath, Project.class); projects = Utils.readPath(spark, inputPath, Project.class);
projects projects