package eu.dnetlib.dhp.actionmanager.fosnodoi;

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

import java.io.IOException;
import java.io.Serializable;
import java.util.*;

import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import com.fasterxml.jackson.databind.ObjectMapper;

import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.utils.*;
import scala.Tuple2;

public class CreateActionSetSparkJob implements Serializable {

	private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);

	private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();

	public static void main(final String[] args) throws IOException, ParseException {

		final ArgumentApplicationParser parser = new ArgumentApplicationParser(
			IOUtils
				.toString(
					Objects
						.requireNonNull(
							CreateActionSetSparkJob.class
								.getResourceAsStream(
									"/eu/dnetlib/dhp/actionmanager/fosnodoi/as_parameters.json"))));

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

		SparkConf conf = new SparkConf();
		runWithSparkSession(
			conf,
			isSparkSessionManaged,
			spark -> createActionSet(spark, inputPath, outputPath));

	}

	private static void createActionSet(SparkSession spark, String inputPath, String outputPath) {
		spark
			.read()
			.textFile(inputPath)
			.map(
				(MapFunction<String, Result>) value -> OBJECT_MAPPER.readValue(value, Result.class),
				Encoders.bean(Result.class))
			.toJavaRDD()
			.map(p -> new AtomicAction(p.getClass(), p))
			.mapToPair(
				aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
					new Text(OBJECT_MAPPER.writeValueAsString(aa))))
			.saveAsHadoopFile(
				outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
	}

}