forked from D-Net/dnet-hadoop
89 lines
2.8 KiB
Java
89 lines
2.8 KiB
Java
|
|
package eu.dnetlib.dhp.ircdl_extention;
|
|
|
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
|
|
|
|
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.Dataset;
|
|
import org.apache.spark.sql.Encoders;
|
|
import org.apache.spark.sql.SaveMode;
|
|
import org.apache.spark.sql.SparkSession;
|
|
|
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
|
import eu.dnetlib.dhp.ircdl_extention.model.Result;
|
|
|
|
public class PrepareNormalizedResultSpark {
|
|
|
|
public static void main(String[] args) throws Exception {
|
|
|
|
String jsonConfiguration = IOUtils
|
|
.toString(
|
|
PrepareNormalizedResultSpark.class
|
|
.getResourceAsStream(
|
|
"/eu/dnetlib/dhp/ircdl_extention/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);
|
|
|
|
final String inputPath = parser.get("inputPath");
|
|
|
|
final String outputPath = parser.get("outputPath");
|
|
|
|
SparkConf conf = new SparkConf();
|
|
conf.set("hive.metastore.uris", "thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083");
|
|
|
|
runWithSparkHiveSession(
|
|
conf,
|
|
isSparkSessionManaged,
|
|
spark -> {
|
|
Utils.removeOutputDir(spark, outputPath);
|
|
execNormalize(spark, outputPath, inputPath);
|
|
});
|
|
}
|
|
|
|
private static void execNormalize(SparkSession spark, String outputPath, String inputPath) {
|
|
Dataset<Result> normalized_result = Utils
|
|
.readPath(spark, inputPath + "publicationsWithOrcid", Result.class)
|
|
.union(Utils.readPath(spark, inputPath + "datasetWithOrcid", Result.class))
|
|
.union(Utils.readPath(spark, inputPath + "softwareWithOrcid", Result.class))
|
|
.union(Utils.readPath(spark, inputPath + "otherWithOrcid", Result.class))
|
|
.map((MapFunction<Result, Result>) r -> {
|
|
r.setName(Utils.normalizeString(r.getName()));
|
|
r.setSurname(Utils.normalizeString(r.getSurname()));
|
|
r.setFullname(Utils.normalizeString(r.getFullname()));
|
|
return r;
|
|
}, Encoders.bean(Result.class));
|
|
|
|
normalized_result
|
|
.write()
|
|
.option("compression", "gzip")
|
|
.mode(SaveMode.Overwrite)
|
|
.json(outputPath + "ResultWithOrcid");
|
|
|
|
normalized_result
|
|
.filter((FilterFunction<Result>) r -> !r.getId().startsWith("50|dedup"))
|
|
.write()
|
|
.option("compression", "gzip")
|
|
.mode(SaveMode.Overwrite)
|
|
.json(outputPath + "collectedResultWithOrcid");
|
|
|
|
normalized_result
|
|
.filter((FilterFunction<Result>) r -> !r.getDeletedbyinference())
|
|
.write()
|
|
.option("compression", "gzip")
|
|
.mode(SaveMode.Overwrite)
|
|
.json(outputPath + "notDeletedByInferenceResultWithOrcid");
|
|
}
|
|
}
|