dhp-graph-dump/dump/src/main/java/eu/dnetlib/dhp/oa/graph/dump/skgif/DumpVenue.java

package eu.dnetlib.dhp.oa.graph.dump.skgif;

import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Datasource;
import eu.dnetlib.dhp.schema.oaf.Journal;
import eu.dnetlib.dhp.skgif.model.*;
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.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.io.Serializable;
import java.util.*;
import java.util.stream.Collectors;

import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;

/**
 * @author miriam.baglioni
 * @Date 21/02/24
 */
public class DumpVenue implements Serializable {
    private static final Logger log = LoggerFactory.getLogger(DumpVenue.class);

    public static void main(String[] args) throws Exception {
        String jsonConfiguration = IOUtils
                .toString(
                        DumpVenue.class
                                .getResourceAsStream(
                                        "/eu/dnetlib/dhp/oa/graph/dump/dump_datasource_parameters.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 inputPath = parser.get("sourcePath");
        log.info("inputPath: {}", inputPath);

        final String workingDir = parser.get("workingDir");
        log.info("workingDir: {}", workingDir);

        final String outputPath = parser.get("outputPath");
        log.info("outputPath: {}", outputPath);

        SparkConf conf = new SparkConf();

        runWithSparkSession(
                conf,
                isSparkSessionManaged,
                spark -> {
                    Utils.removeOutputDir(spark, outputPath + "Venue");

                    mapDatasource(spark, inputPath, outputPath, workingDir);
                });
    }

    private static void mapDatasource(SparkSession spark, String inputPath,  String outputPath, String workingDir) {
        Utils.readPath(spark, inputPath + "datasource", Datasource.class)
                .filter((FilterFunction<Datasource>) d -> !d.getDataInfo().getInvisible() && ! d.getDataInfo().getDeletedbyinference()
                && d.getEoscdatasourcetype().getClassid().equalsIgnoreCase("Journal archive"))
                .map((MapFunction<Datasource, eu.dnetlib.dhp.skgif.model.Venue>) d -> {
                    Venue venue = new Venue();
                    if(Optional.ofNullable(d.getJournal().getIssnPrinted()).isPresent())
                        venue.setLocal_identifier(Utils.getIdentifier(Prefixes.VENUE, d.getJournal().getIssnPrinted()));
                    else if(Optional.ofNullable(d.getJournal().getIssnOnline()).isPresent())
                        venue.setLocal_identifier(Utils.getIdentifier(Prefixes.VENUE, d.getJournal().getIssnOnline()));
                    venue.setIdentifiers(getVenueIdentifier(d.getJournal()));
                    venue.setName(d.getOfficialname().getValue());
                    venue.setType(VenueType.JOURNAL.label);
                    //todo add map for publisher. Get from results?
                    venue.setPublisher("find it from result");
                    venue.setAcronym(null);
                    venue.setSeries(null);
                    venue.setIs_currently_full_oa(null);
                    venue.setCreation_date(null);
                    venue.setContributions(null);
                    return venue;
                }, Encoders.bean(Venue.class) )
                .write()
                .mode(SaveMode.Overwrite)
                .option("compression","gzip")
                .json(workingDir + "Venues");

        Utils.readPath(spark, workingDir + "Venues", Venue.class)
                .groupByKey((MapFunction<Venue, String>)v -> v.getLocal_identifier() , Encoders.STRING())
                .mapGroups((MapGroupsFunction<String, Venue, Venue>) (k,v) -> v.next(), Encoders.bean(Venue.class) )
                .write()
                .mode(SaveMode.Overwrite)
                .option("compression","gzip")
                .json(outputPath + "Venues");
    }

    private static List<Identifier> getVenueIdentifier(Journal journal) {
        List<Identifier> identifiers = new ArrayList<>();
        if (Optional.ofNullable((journal.getIssnOnline())).isPresent())
            identifiers.add(Identifier.newInstance(VenueIdentifierType.EISSN.label, journal.getIssnOnline()));
        if(Optional.ofNullable(journal.getIssnPrinted()).isPresent())
            identifiers.add(Identifier.newInstance(VenueIdentifierType.ISSN.label,  journal.getIssnPrinted()));
        if (Optional.ofNullable(journal.getIssnLinking()).isPresent())
            identifiers.add(Identifier.newInstance(VenueIdentifierType.LISSN.label, journal.getIssnLinking()));
        return identifiers;
    }

    private static List<String> getResearchProductAccessPolicy(List<String> value) {

        return value.stream().map(v -> getResearchProductAccessPolicy(v)).filter(Objects::nonNull)
                .map(v -> v.get(0)).distinct().collect(Collectors.toList());
    }
    private static List<String> getResearchProductAccessPolicy(String value) {
        // "databaseaccesstype if open => open access (https://vocabularies.coar-repositories.org/access_rights/c_abf2/)
        //if restricted => restricted access (https://vocabularies.coar-repositories.org/access_rights/c_16ec/)
        //if closed => metadata only access (https://vocabularies.coar-repositories.org/access_rights/c_14cb/) "
        switch(value){
            case "open"://(https://vocabularies.coar-repositories.org/access_rights/c_abf2/)
                return Arrays.asList("open access");
            case "restricted"://(https://vocabularies.coar-repositories.org/access_rights/c_16ec/)
                return Arrays.asList("restricted access");
            case "closed"://(https://vocabularies.coar-repositories.org/access_rights/c_14cb/)
                return Arrays.asList("metadata only access");
            default:
                return null;
        }
    }

    private static List<String> getEoscProductType(List<String> researchentitytypes) {

        List<String> eoscProductType = new ArrayList<>();
        if(researchentitytypes != null) {

            if (researchentitytypes.contains("Software"))
                eoscProductType.add("Research Software");
            if (researchentitytypes.contains("Research Publications") || researchentitytypes.contains("Literature"))
                eoscProductType.add("Research Literature");
            if (researchentitytypes.contains("Research Data"))
                eoscProductType.add("Research Data");
            if (researchentitytypes.contains("Organization") ||
                    researchentitytypes.contains("Organizations") ||
                    researchentitytypes.contains("Services") ||
                    researchentitytypes.contains("Projects"))
                eoscProductType.add("Other research product");
        }
        return eoscProductType;
    }
}