90 lines
2.8 KiB
Java
90 lines
2.8 KiB
Java
|
|
package eu.dnetlib.dhp.bypassactionset.bipfinder;
|
|
|
|
import static eu.dnetlib.dhp.bypassactionset.Utils.getIdentifier;
|
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
|
|
|
import java.io.Serializable;
|
|
import java.util.Optional;
|
|
import java.util.stream.Collectors;
|
|
|
|
import org.apache.commons.io.IOUtils;
|
|
import org.apache.spark.SparkConf;
|
|
import org.apache.spark.api.java.JavaRDD;
|
|
import org.apache.spark.api.java.JavaSparkContext;
|
|
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 eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
|
import eu.dnetlib.dhp.bypassactionset.model.BipDeserialize;
|
|
import eu.dnetlib.dhp.bypassactionset.model.BipScore;
|
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
|
|
|
public class PrepareBipFinder implements Serializable {
|
|
|
|
private static final Logger log = LoggerFactory.getLogger(SparkUpdateBip.class);
|
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
|
|
|
public static <I extends Result> void main(String[] args) throws Exception {
|
|
|
|
String jsonConfiguration = IOUtils
|
|
.toString(
|
|
SparkUpdateBip.class
|
|
.getResourceAsStream(
|
|
"/eu/dnetlib/dhp/bypassactionset/bip_prepare_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("inputPath");
|
|
log.info("inputPath {}: ", inputPath);
|
|
|
|
final String outputPath = parser.get("outputPath");
|
|
log.info("outputPath {}: ", outputPath);
|
|
|
|
SparkConf conf = new SparkConf();
|
|
|
|
runWithSparkSession(
|
|
conf,
|
|
isSparkSessionManaged,
|
|
spark -> {
|
|
|
|
prepareResults(spark, inputPath, outputPath);
|
|
});
|
|
}
|
|
|
|
private static <I extends Result> void prepareResults(SparkSession spark, String inputPath, String outputPath) {
|
|
|
|
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
|
|
|
JavaRDD<BipDeserialize> bipDeserializeJavaRDD = sc
|
|
.textFile(inputPath)
|
|
.map(item -> OBJECT_MAPPER.readValue(item, BipDeserialize.class));
|
|
|
|
spark
|
|
.createDataset(bipDeserializeJavaRDD.flatMap(entry -> entry.keySet().stream().map(key -> {
|
|
BipScore bs = new BipScore();
|
|
bs.setId(getIdentifier(key));
|
|
bs.setScoreList(entry.get(key));
|
|
return bs;
|
|
}).collect(Collectors.toList()).iterator()).rdd(), Encoders.bean(BipScore.class))
|
|
.write()
|
|
.mode(SaveMode.Overwrite)
|
|
.option("compression", "gzip")
|
|
.json(outputPath);
|
|
}
|
|
}
|