93 lines
2.4 KiB
Java
93 lines
2.4 KiB
Java
|
|
package eu.dnetlib.dhp.oa.graph.dump;
|
|
|
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
|
|
|
import java.io.Serializable;
|
|
import java.util.ArrayList;
|
|
import java.util.List;
|
|
import java.util.Optional;
|
|
|
|
import org.apache.commons.io.IOUtils;
|
|
import org.apache.commons.lang3.StringUtils;
|
|
import org.apache.spark.SparkConf;
|
|
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.*;
|
|
import org.slf4j.Logger;
|
|
import org.slf4j.LoggerFactory;
|
|
|
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
|
import eu.dnetlib.dhp.schema.oaf.Relation;
|
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
|
import scala.Tuple2;
|
|
|
|
/**
|
|
* @author miriam.baglioni
|
|
* @Date 22/09/23
|
|
*/
|
|
public class SparkCopyGraph implements Serializable {
|
|
|
|
private static final Logger log = LoggerFactory.getLogger(SparkCopyGraph.class);
|
|
|
|
public static void main(String[] args) throws Exception {
|
|
|
|
String jsonConfiguration = IOUtils
|
|
.toString(
|
|
SparkCopyGraph.class
|
|
.getResourceAsStream(
|
|
"/eu/dnetlib/dhp/oa/graph/dump/copygraph_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 hivePath = parser.get("hivePath");
|
|
log.info("hivePath: {}", hivePath);
|
|
|
|
final String outputPath = parser.get("outputPath");
|
|
log.info("outputPath: {}", outputPath);
|
|
|
|
SparkConf conf = new SparkConf();
|
|
|
|
runWithSparkSession(
|
|
conf,
|
|
isSparkSessionManaged,
|
|
spark ->
|
|
|
|
execCopy(
|
|
spark,
|
|
hivePath,
|
|
outputPath));
|
|
}
|
|
|
|
private static void execCopy(SparkSession spark, String hivePath, String outputPath) {
|
|
|
|
ModelSupport.oafTypes.entrySet().parallelStream().forEach(entry -> {
|
|
String entityType = entry.getKey();
|
|
Class<?> clazz = entry.getValue();
|
|
// if (!entityType.equalsIgnoreCase("relation")) {
|
|
spark
|
|
.read()
|
|
.schema(Encoders.bean(clazz).schema())
|
|
.parquet(hivePath + "/" + entityType)
|
|
.write()
|
|
.mode(SaveMode.Overwrite)
|
|
.option("compression", "gzip")
|
|
.json(outputPath + "/" + entityType);
|
|
|
|
});
|
|
|
|
}
|
|
|
|
}
|