D-Net
/
dnet-hadoop
13
4
Fork 10
Code Issues 14 Pull Requests 8 Projects 2 Releases 1 Wiki Activity

[Graph DUMP] add code to produce the delta of new projects with respect to the previous delta/dump #221

Merged
claudio.atzori merged 4 commits from dump_delta_projects into master 2022-07-01 10:30:11 +02:00
Conversation 0 Commits 4 Files Changed 8 +60 -61
1 changed files with 60 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 71744a1f52 - Show all commits

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