126 lines
3.5 KiB
Java
126 lines
3.5 KiB
Java
|
|
package eu.dnetlib.dhp.oa.graph.dump.skgif;
|
|
|
|
import java.io.IOException;
|
|
import java.io.Serializable;
|
|
import java.nio.file.Files;
|
|
import java.nio.file.Path;
|
|
|
|
import org.apache.commons.io.FileUtils;
|
|
import org.apache.spark.SparkConf;
|
|
import org.apache.spark.api.java.JavaRDD;
|
|
import org.apache.spark.api.java.JavaSparkContext;
|
|
import org.apache.spark.api.java.function.ForeachFunction;
|
|
import org.apache.spark.sql.Dataset;
|
|
import org.apache.spark.sql.Encoders;
|
|
import org.apache.spark.sql.SparkSession;
|
|
import org.junit.jupiter.api.AfterAll;
|
|
import org.junit.jupiter.api.Assertions;
|
|
import org.junit.jupiter.api.BeforeAll;
|
|
import org.junit.jupiter.api.Test;
|
|
import org.slf4j.Logger;
|
|
import org.slf4j.LoggerFactory;
|
|
|
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
|
|
|
import eu.dnetlib.dhp.oa.graph.dump.filterentities.SelectEOSCEntities;
|
|
import eu.dnetlib.dhp.skgif.model.Datasource;
|
|
import eu.dnetlib.dhp.skgif.model.Venue;
|
|
|
|
/**
|
|
* @author miriam.baglioni
|
|
* @Date 22/02/24
|
|
*/
|
|
public class DumpVenueTest implements Serializable {
|
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
|
|
|
private static SparkSession spark;
|
|
|
|
private static Path workingDir;
|
|
|
|
private static final Logger log = LoggerFactory.getLogger(DumpVenueTest.class);
|
|
|
|
@BeforeAll
|
|
public static void beforeAll() throws IOException {
|
|
workingDir = Files.createTempDirectory(DumpVenueTest.class.getSimpleName());
|
|
log.info("using work dir {}", workingDir);
|
|
|
|
SparkConf conf = new SparkConf();
|
|
conf.setAppName(DumpVenueTest.class.getSimpleName());
|
|
|
|
conf.setMaster("local[*]");
|
|
conf.set("spark.driver.host", "localhost");
|
|
conf.set("hive.metastore.local", "true");
|
|
conf.set("spark.ui.enabled", "false");
|
|
conf.set("spark.sql.warehouse.dir", workingDir.toString());
|
|
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
|
|
|
|
spark = SparkSession
|
|
.builder()
|
|
.appName(DumpVenueTest.class.getSimpleName())
|
|
.config(conf)
|
|
.getOrCreate();
|
|
}
|
|
|
|
@AfterAll
|
|
public static void afterAll() throws IOException {
|
|
FileUtils.deleteDirectory(workingDir.toFile());
|
|
spark.stop();
|
|
}
|
|
|
|
@Test
|
|
public void testDumpVenueApi() throws Exception {
|
|
final String sourcePath = getClass()
|
|
.getResource("/eu/dnetlib/dhp/oa/graph/dump/skgif/graphForAPIExample/")
|
|
.getPath();
|
|
|
|
final String workingDir = getClass()
|
|
.getResource("/eu/dnetlib/dhp/oa/graph/dump/skgif/workingDirApiExample/")
|
|
.getPath();
|
|
|
|
DumpVenue
|
|
.main(
|
|
new String[] {
|
|
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
|
"-sourcePath", sourcePath,
|
|
"-outputPath", "/tmp/",
|
|
"-workingDir", workingDir
|
|
|
|
});
|
|
|
|
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
|
|
|
JavaRDD<Venue> datasource = sc
|
|
.textFile(workingDir.toString() + "Venues")
|
|
.map(item -> OBJECT_MAPPER.readValue(item, Venue.class));
|
|
|
|
Dataset<Venue> datasourceDataset = spark.createDataset(datasource.rdd(), Encoders.bean(Venue.class));
|
|
|
|
datasourceDataset
|
|
.foreach((ForeachFunction<Venue>) d -> System.out.println(OBJECT_MAPPER.writeValueAsString(d)));
|
|
|
|
}
|
|
|
|
@Test
|
|
public void testSelectEoscResults() throws Exception {
|
|
final String sourcePath = getClass()
|
|
.getResource("/eu/dnetlib/dhp/oa/graph/dump/skgif/graphForAPIExample/")
|
|
.getPath();
|
|
|
|
final String workingDir = getClass()
|
|
.getResource("/eu/dnetlib/dhp/oa/graph/dump/skgif/workingDirApiExample/")
|
|
.getPath();
|
|
|
|
SelectEOSCEntities
|
|
.main(
|
|
new String[] {
|
|
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
|
"-sourcePath", sourcePath,
|
|
"-filterPath", "/tmp/",
|
|
"-workingDir", workingDir
|
|
|
|
});
|
|
|
|
}
|
|
}
|