134 lines
4.7 KiB
Java
134 lines
4.7 KiB
Java
|
|
package eu.dnetlib.dhp.oa.graph.dump.csv;
|
|
|
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
|
|
|
import java.io.Serializable;
|
|
import java.util.Optional;
|
|
|
|
import org.apache.commons.io.IOUtils;
|
|
import org.apache.spark.SparkConf;
|
|
import org.apache.spark.api.java.function.MapFunction;
|
|
import org.apache.spark.api.java.function.MapGroupsFunction;
|
|
import org.apache.spark.sql.Dataset;
|
|
import org.apache.spark.sql.Encoders;
|
|
import org.apache.spark.sql.Row;
|
|
import org.apache.spark.sql.SaveMode;
|
|
import org.apache.spark.sql.SparkSession;
|
|
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.oa.graph.dump.csv.model.CSVAuthor;
|
|
import eu.dnetlib.dhp.oa.graph.dump.csv.model.CSVPid;
|
|
import eu.dnetlib.dhp.oa.graph.dump.csv.model.CSVRelResAut;
|
|
import eu.dnetlib.dhp.oa.graph.dump.csv.model.CSVResult;
|
|
import eu.dnetlib.dhp.schema.oaf.*;
|
|
|
|
/**
|
|
* @author miriam.baglioni
|
|
* @Date 10/05/23
|
|
*/
|
|
//STEP 4
|
|
public class SparkMoveOnSigleDir implements Serializable {
|
|
|
|
// All the products saved in different directories are put under the same one.
|
|
// For the authors also a step of reconciliation mast be done, since the same author id can be saved in more than
|
|
// one directory
|
|
|
|
private static final Logger log = LoggerFactory.getLogger(SparkMoveOnSigleDir.class);
|
|
|
|
public static void main(String[] args) throws Exception {
|
|
String jsonConfiguration = IOUtils
|
|
.toString(
|
|
SparkMoveOnSigleDir.class
|
|
.getResourceAsStream(
|
|
"/eu/dnetlib/dhp/oa/graph/dump/input_dump_csv_ste4.json"));
|
|
|
|
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
|
parser.parseArgument(args);
|
|
|
|
Boolean isSparkSessionManaged = Optional
|
|
.ofNullable(parser.get("isSparkSessionManaged"))
|
|
.map(Boolean::valueOf)
|
|
.orElse(Boolean.TRUE);
|
|
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
|
|
|
final String workingPath = parser.get("workingPath");
|
|
log.info("workingPath: {}", workingPath);
|
|
|
|
final String outputPath = parser.get("outputPath");
|
|
log.info("outputPath: {}", outputPath);
|
|
|
|
SparkConf conf = new SparkConf();
|
|
|
|
runWithSparkSession(
|
|
conf,
|
|
isSparkSessionManaged,
|
|
spark -> {
|
|
// Utils.removeOutputDir(spark, outputPath);
|
|
run(spark, outputPath, workingPath);
|
|
|
|
});
|
|
|
|
}
|
|
|
|
private static <R extends Result> void run(SparkSession spark, String outputPath,
|
|
String workingPath) {
|
|
|
|
Utils
|
|
.readPath(spark, workingPath + "/publication/result", CSVResult.class)
|
|
.union(Utils.readPath(spark, workingPath + "/dataset/result", CSVResult.class))
|
|
.union(Utils.readPath(spark, workingPath + "/software/result", CSVResult.class))
|
|
.union(Utils.readPath(spark, workingPath + "/otherresearchproduct/result", CSVResult.class))
|
|
.write()
|
|
.mode(SaveMode.Overwrite)
|
|
.option("header", "true")
|
|
.option("delimiter", Constants.SEP)
|
|
.option("compression", "gzip")
|
|
.csv(outputPath + "/result");
|
|
|
|
Utils
|
|
.readPath(spark, workingPath + "/publication/result_pid", CSVPid.class)
|
|
.union(Utils.readPath(spark, workingPath + "/dataset/result_pid", CSVPid.class))
|
|
.union(Utils.readPath(spark, workingPath + "/software/result_pid", CSVPid.class))
|
|
.union(Utils.readPath(spark, workingPath + "/otherresearchproduct/result_pid", CSVPid.class))
|
|
.write()
|
|
.mode(SaveMode.Overwrite)
|
|
.option("header", "true")
|
|
.option("delimiter", Constants.SEP)
|
|
.option("compression", "gzip")
|
|
.csv(outputPath + "/result_pid");
|
|
|
|
Utils
|
|
.readPath(spark, workingPath + "/publication/result_author", CSVRelResAut.class)
|
|
.union(Utils.readPath(spark, workingPath + "/dataset/result_author", CSVRelResAut.class))
|
|
.union(Utils.readPath(spark, workingPath + "/software/result_author", CSVRelResAut.class))
|
|
.union(Utils.readPath(spark, workingPath + "/otherresearchproduct/result_author", CSVRelResAut.class))
|
|
.write()
|
|
.mode(SaveMode.Overwrite)
|
|
.option("header", "true")
|
|
.option("delimiter", Constants.SEP)
|
|
.option("compression", "gzip")
|
|
.csv(outputPath + "/result_author");
|
|
|
|
Utils
|
|
.readPath(spark, workingPath + "/publication/author", CSVAuthor.class)
|
|
.union(Utils.readPath(spark, workingPath + "/dataset/author", CSVAuthor.class))
|
|
.union(Utils.readPath(spark, workingPath + "/software/author", CSVAuthor.class))
|
|
.union(Utils.readPath(spark, workingPath + "/otherresearchproduct/author", CSVAuthor.class))
|
|
.groupByKey((MapFunction<CSVAuthor, String>) r -> r.getId(), Encoders.STRING())
|
|
.mapGroups(
|
|
(MapGroupsFunction<String, CSVAuthor, CSVAuthor>) (k, it) -> it.next(), Encoders.bean(CSVAuthor.class))
|
|
.write()
|
|
.mode(SaveMode.Overwrite)
|
|
.option("header", "true")
|
|
.option("delimiter", Constants.SEP)
|
|
.option("compression", "gzip")
|
|
.csv(outputPath + "/author");
|
|
|
|
}
|
|
|
|
}
|