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

import java.io.Serializable;
import java.util.List;
import java.util.Optional;

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.SparkSession;

import com.fasterxml.jackson.databind.ObjectMapper;

import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.skgif.model.Prefixes;
import eu.dnetlib.dhp.utils.DHPUtils;
import scala.Tuple2;

/**
 * @author miriam.baglioni
 * @Date 16/02/24
 */
public class Utils implements Serializable {
	public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();

	private Utils() {
	}

	public static void removeOutputDir(SparkSession spark, String path) {
		HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
	}

	public static <R> Dataset<R> readPath(
		SparkSession spark, String inputPath, Class<R> clazz) {
		return spark
			.read()
			.textFile(inputPath)
			.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
	}

	public static Tuple2<String, Boolean> getOrcid(List<StructuredProperty> pid) {
		if (!Optional.ofNullable(pid).isPresent())
			return null;
		if (pid.size() == 0)
			return null;
		for (StructuredProperty p : pid) {
			if (p.getQualifier().getClassid().equals(ModelConstants.ORCID)) {
				return new Tuple2<>(p.getValue(), Boolean.TRUE);
			}
		}
		for (StructuredProperty p : pid) {
			if (p.getQualifier().getClassid().equals(ModelConstants.ORCID_PENDING)) {
				return new Tuple2<>(p.getValue(), Boolean.FALSE);
			}
		}
		return null;
	}

	public static String getIdentifier(Prefixes entity, String id) {
		return entity.label + DHPUtils.md5(id);

	}
}