137 lines
4.4 KiB
Java
137 lines
4.4 KiB
Java
|
|
package eu.dnetlib.dhp.oa.graph.dump.country;
|
|
|
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
|
|
|
import java.io.Serializable;
|
|
import java.util.*;
|
|
|
|
import javax.rmi.CORBA.Util;
|
|
|
|
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.sql.Dataset;
|
|
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 com.fasterxml.jackson.databind.ObjectMapper;
|
|
import com.google.gson.Gson;
|
|
import com.jayway.jsonpath.DocumentContext;
|
|
import com.jayway.jsonpath.JsonPath;
|
|
|
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
|
import eu.dnetlib.dhp.oa.graph.dump.Constants;
|
|
import eu.dnetlib.dhp.oa.graph.dump.ResultMapper;
|
|
import eu.dnetlib.dhp.oa.graph.dump.Utils;
|
|
import eu.dnetlib.dhp.oa.graph.dump.subset.MasterDuplicate;
|
|
import eu.dnetlib.dhp.oa.graph.dump.subset.SparkDumpResult;
|
|
import eu.dnetlib.dhp.oa.graph.dump.subset.criteria.VerbResolver;
|
|
import eu.dnetlib.dhp.oa.graph.dump.subset.criteria.VerbResolverFactory;
|
|
import eu.dnetlib.dhp.oa.graph.dump.subset.selectionconstraints.Param;
|
|
import eu.dnetlib.dhp.oa.graph.dump.subset.selectionconstraints.SelectionConstraints;
|
|
import eu.dnetlib.dhp.oa.model.graph.GraphResult;
|
|
import eu.dnetlib.dhp.schema.oaf.DataInfo;
|
|
import eu.dnetlib.dhp.schema.oaf.KeyValue;
|
|
import scala.Tuple2;
|
|
|
|
/**
|
|
* @author miriam.baglioni
|
|
* @Date 27/04/23
|
|
* Selects the results having in the country the given country
|
|
*/
|
|
public class SparkFindResultWithCountry implements Serializable {
|
|
private static final Logger log = LoggerFactory.getLogger(SparkFindResultWithCountry.class);
|
|
|
|
public static final String COMPRESSION = "compression";
|
|
public static final String GZIP = "gzip";
|
|
|
|
public static void main(String[] args) throws Exception {
|
|
String jsonConfiguration = IOUtils
|
|
.toString(
|
|
SparkFindResultWithCountry.class
|
|
.getResourceAsStream(
|
|
"/eu/dnetlib/dhp/oa/graph/dump/result_country_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 outputPath = parser.get("outputPath");
|
|
log.info("outputPath: {}", outputPath);
|
|
|
|
final String resultType = parser.get("resultType");
|
|
log.info("resultType: {}", resultType);
|
|
|
|
final String resultClassName = parser.get("resultTableName");
|
|
log.info("resultTableName: {}", resultClassName);
|
|
|
|
final String preparedInfoPath = parser.get("resultWithCountry");
|
|
|
|
Class<? extends eu.dnetlib.dhp.schema.oaf.Result> inputClazz = (Class<? extends eu.dnetlib.dhp.schema.oaf.Result>) Class
|
|
.forName(resultClassName);
|
|
|
|
run(
|
|
isSparkSessionManaged, inputPath, outputPath, inputClazz,
|
|
resultType, preparedInfoPath);
|
|
|
|
}
|
|
|
|
private static void run(Boolean isSparkSessionManaged, String inputPath, String outputPath,
|
|
|
|
Class<? extends eu.dnetlib.dhp.schema.oaf.Result> inputClazz, String resultType, String preparedInfoPath) {
|
|
SparkConf conf = new SparkConf();
|
|
|
|
runWithSparkSession(
|
|
conf,
|
|
isSparkSessionManaged,
|
|
spark -> {
|
|
Utils.removeOutputDir(spark, outputPath + "/original/" + resultType);
|
|
|
|
resultDump(
|
|
spark, inputPath, outputPath, inputClazz, resultType, preparedInfoPath);
|
|
});
|
|
|
|
}
|
|
|
|
public static <I extends eu.dnetlib.dhp.schema.oaf.Result> void resultDump(
|
|
SparkSession spark,
|
|
String inputPath,
|
|
String outputPath,
|
|
Class<I> inputClazz,
|
|
|
|
String resultType,
|
|
|
|
String preparedInfoPath) {
|
|
|
|
Dataset<String> resultsWithCountry = spark.read().textFile(preparedInfoPath).distinct();
|
|
|
|
Dataset<I> result = Utils
|
|
.readPath(spark, inputPath, inputClazz)
|
|
.filter(
|
|
(FilterFunction<I>) r -> !r.getDataInfo().getInvisible() && !r.getDataInfo().getDeletedbyinference());
|
|
|
|
resultsWithCountry
|
|
.joinWith(result, resultsWithCountry.col("value").equalTo(result.col("id")))
|
|
.map((MapFunction<Tuple2<String, I>, I>) t2 -> t2._2(), Encoders.bean(inputClazz))
|
|
.write()
|
|
.mode(SaveMode.Overwrite)
|
|
.option("compression", "gzip")
|
|
.json(outputPath + "/original/" + resultType);
|
|
|
|
}
|
|
|
|
}
|