You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
90 lines
2.9 KiB
Java
90 lines
2.9 KiB
Java
|
|
package eu.dnetlib.dhp.oa.graph.dump.eosc;
|
|
|
|
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.FilterFunction;
|
|
import org.apache.spark.api.java.function.MapFunction;
|
|
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 eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
|
import eu.dnetlib.dhp.eosc.model.EoscResult;
|
|
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.model.graph.GraphResult;
|
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
|
|
|
/**
|
|
* @author miriam.baglioni
|
|
* @Date 27/07/22
|
|
*/
|
|
public class SelectEoscResultsJobStep1 implements Serializable {
|
|
private static final Logger log = LoggerFactory.getLogger(SelectEoscResultsJobStep1.class);
|
|
|
|
public static void main(String[] args) throws Exception {
|
|
String jsonConfiguration = IOUtils
|
|
.toString(
|
|
SelectEoscResultsJobStep1.class
|
|
.getResourceAsStream(
|
|
"/eu/dnetlib/dhp/oa/graph/dump/eosc_select_result_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 resultClassName = parser.get("resultTableName");
|
|
log.info("resultTableName: {}", resultClassName);
|
|
|
|
Class<? extends Result> inputClazz = (Class<? extends Result>) Class.forName(resultClassName);
|
|
|
|
SparkConf conf = new SparkConf();
|
|
|
|
runWithSparkSession(
|
|
conf,
|
|
isSparkSessionManaged,
|
|
spark -> {
|
|
Utils.removeOutputDir(spark, outputPath);
|
|
selectEoscResults(spark, inputPath, outputPath, inputClazz);
|
|
});
|
|
}
|
|
|
|
private static <R extends Result> void selectEoscResults(SparkSession spark, String inputPath, String outputPath,
|
|
Class<R> inputClazz) {
|
|
Utils
|
|
.readPath(spark, inputPath, inputClazz)
|
|
.filter(
|
|
(FilterFunction<R>) r -> !r.getDataInfo().getDeletedbyinference() && !r.getDataInfo().getInvisible()
|
|
&& r.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
|
|
.map(
|
|
(MapFunction<R, EoscResult>) r -> (EoscResult) ResultMapper
|
|
.map(r, null, Constants.DUMPTYPE.EOSC.getType()),
|
|
Encoders.bean(EoscResult.class))
|
|
.write()
|
|
.mode(SaveMode.Overwrite)
|
|
.option("compression", "gzip")
|
|
.json(outputPath);
|
|
}
|
|
|
|
}
|