forked from D-Net/dnet-hadoop
refactoring
This commit is contained in:
parent
87a9f616ae
commit
e758d5d9b4
|
@ -6,9 +6,9 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
|||
import java.io.Serializable;
|
||||
import java.util.Optional;
|
||||
|
||||
import eu.dnetlib.dhp.oa.graph.dump.Constants;
|
||||
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.api.java.function.MapGroupsFunction;
|
||||
import org.apache.spark.sql.Dataset;
|
||||
|
@ -64,11 +64,11 @@ public class SparkResultLinkedToProject implements Serializable {
|
|||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
Utils.removeOutputDir(spark, outputPath);
|
||||
writeResultsLikedToProjects(spark, inputClazz, inputPath, outputPath, relationPath);
|
||||
writeResultsLinkedToProjects(spark, inputClazz, inputPath, outputPath, relationPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static <R extends Result> void writeResultsLikedToProjects(SparkSession spark, Class<R> inputClazz,
|
||||
private static <R extends Result> void writeResultsLinkedToProjects(SparkSession spark, Class<R> inputClazz,
|
||||
String inputPath, String outputPath, String relationPath) {
|
||||
|
||||
Dataset<R> results = Utils
|
||||
|
@ -76,7 +76,7 @@ public class SparkResultLinkedToProject implements Serializable {
|
|||
.filter("dataInfo.deletedbyinference = false and datainfo.invisible = false");
|
||||
Dataset<Relation> relations = Utils
|
||||
.readPath(spark, relationPath, Relation.class)
|
||||
.filter("dataInfo.deletedbyinference = false and lower(relClass) = 'isproducedby'");
|
||||
.filter("dataInfo.deletedbyinference = false and lower(relClass) = '" + Constants.RESULT_PROJECT_IS_PRODUCED_BY.toLowerCase() + "'");
|
||||
|
||||
relations
|
||||
.joinWith(
|
||||
|
|
Loading…
Reference in New Issue