177 lines
8.0 KiB
Java
177 lines
8.0 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.skgif.model.Datasource;
|
|
import eu.dnetlib.dhp.skgif.model.Organization;
|
|
|
|
/**
|
|
* @author miriam.baglioni
|
|
* @Date 22/02/24
|
|
*/
|
|
public class DumpDatasourceTest 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(DumpDatasourceTest.class);
|
|
|
|
@BeforeAll
|
|
public static void beforeAll() throws IOException {
|
|
workingDir = Files.createTempDirectory(DumpDatasourceTest.class.getSimpleName());
|
|
log.info("using work dir {}", workingDir);
|
|
|
|
SparkConf conf = new SparkConf();
|
|
conf.setAppName(DumpDatasourceTest.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(DumpDatasourceTest.class.getSimpleName())
|
|
.config(conf)
|
|
.getOrCreate();
|
|
}
|
|
|
|
@AfterAll
|
|
public static void afterAll() throws IOException {
|
|
FileUtils.deleteDirectory(workingDir.toFile());
|
|
spark.stop();
|
|
}
|
|
|
|
@Test
|
|
public void testDumpDatasource() throws Exception {
|
|
final String sourcePath = getClass()
|
|
.getResource("/eu/dnetlib/dhp/oa/graph/dump/skgif/graph/")
|
|
.getPath();
|
|
|
|
DumpDatasource
|
|
.main(
|
|
new String[] {
|
|
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
|
"-sourcePath", sourcePath,
|
|
"-outputPath", workingDir.toString() + "/"
|
|
|
|
});
|
|
|
|
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
|
|
|
JavaRDD<Datasource> datasource = sc
|
|
.textFile(workingDir.toString() + "/Datasource")
|
|
.map(item -> OBJECT_MAPPER.readValue(item, Datasource.class));
|
|
|
|
Dataset<Datasource> datasourceDataset = spark.createDataset(datasource.rdd(), Encoders.bean(Datasource.class));
|
|
Assertions.assertEquals(5, datasourceDataset.count());
|
|
datasourceDataset.show(false);
|
|
// Assertions.assertEquals(7, relationDataset.count());
|
|
// RelationPerProduct temp = relationDataset.filter((FilterFunction<RelationPerProduct>) r -> r.getResultId().equalsIgnoreCase("50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9")).first();
|
|
// Assertions.assertEquals(3, temp.getFunding().size()+temp.getRelatedProduct().size()+temp.getOrganizations().size());
|
|
// Assertions.assertEquals(1, temp.getFunding().size());
|
|
// Assertions.assertEquals(2, temp.getRelatedProduct().size());
|
|
// Assertions.assertEquals(1, temp.getRelatedProduct().stream().filter(rp -> rp.getRelation_type().equalsIgnoreCase("issupplementedby")).count());
|
|
// Assertions.assertEquals(1, temp.getRelatedProduct().stream().filter(rp -> rp.getRelation_type().equalsIgnoreCase("isdocumentedby")).count());
|
|
//
|
|
// JavaRDD<ResearchProduct> researchProduct = sc
|
|
// .textFile(workingDir.toString() + "/publication/researchproduct")
|
|
// .map(item -> OBJECT_MAPPER.readValue(item, ResearchProduct.class));
|
|
//
|
|
// org.apache.spark.sql.Dataset<ResearchProduct> researchProductDataset = spark
|
|
// .createDataset(researchProduct.rdd(), Encoders.bean(ResearchProduct.class));
|
|
//
|
|
// Assertions.assertEquals(1, researchProductDataset.filter((FilterFunction<ResearchProduct>) p -> p.getLocal_identifier().equalsIgnoreCase(Utils.getIdentifier(Prefixes.RESEARCH_PRODUCT, "50|DansKnawCris::0224aae28af558f21768dbc6439c7a95"))).count());
|
|
// ResearchProduct product = researchProductDataset.filter((FilterFunction<ResearchProduct>) p -> p.getLocal_identifier().equalsIgnoreCase(Utils.getIdentifier(Prefixes.RESEARCH_PRODUCT, "50|DansKnawCris::0224aae28af558f21768dbc6439c7a95"))).first();
|
|
// Assertions.assertEquals(2, product.getRelevant_organizations().size());
|
|
// Assertions.assertEquals(1, product.getFunding().size());
|
|
// Assertions.assertEquals(0, product.getRelated_products().size());
|
|
// Assertions.assertEquals(1, product.getContributions().size());
|
|
// Assertions.assertEquals(2, product.getManifestations().size());
|
|
//
|
|
// researchProductDataset.show(false);
|
|
//
|
|
//
|
|
|
|
}
|
|
|
|
@Test
|
|
public void testDumpDatasourceComplete() throws Exception {
|
|
final String sourcePath = getClass()
|
|
.getResource("/eu/dnetlib/dhp/oa/graph/dump/skgif/graph_complete_entities/")
|
|
.getPath();
|
|
|
|
DumpDatasource
|
|
.main(
|
|
new String[] {
|
|
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
|
"-sourcePath", sourcePath,
|
|
"-outputPath", workingDir.toString() + "/"
|
|
|
|
});
|
|
|
|
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
|
|
|
JavaRDD<Datasource> datasource = sc
|
|
.textFile(workingDir.toString() + "/Datasource")
|
|
.map(item -> OBJECT_MAPPER.readValue(item, Datasource.class));
|
|
|
|
Dataset<Datasource> datasourceDataset = spark.createDataset(datasource.rdd(), Encoders.bean(Datasource.class));
|
|
|
|
datasourceDataset
|
|
.foreach((ForeachFunction<Datasource>) d -> System.out.println(OBJECT_MAPPER.writeValueAsString(d)));
|
|
// Assertions.assertEquals(7, relationDataset.count());
|
|
// RelationPerProduct temp = relationDataset.filter((FilterFunction<RelationPerProduct>) r -> r.getResultId().equalsIgnoreCase("50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9")).first();
|
|
// Assertions.assertEquals(3, temp.getFunding().size()+temp.getRelatedProduct().size()+temp.getOrganizations().size());
|
|
// Assertions.assertEquals(1, temp.getFunding().size());
|
|
// Assertions.assertEquals(2, temp.getRelatedProduct().size());
|
|
// Assertions.assertEquals(1, temp.getRelatedProduct().stream().filter(rp -> rp.getRelation_type().equalsIgnoreCase("issupplementedby")).count());
|
|
// Assertions.assertEquals(1, temp.getRelatedProduct().stream().filter(rp -> rp.getRelation_type().equalsIgnoreCase("isdocumentedby")).count());
|
|
//
|
|
// JavaRDD<ResearchProduct> researchProduct = sc
|
|
// .textFile(workingDir.toString() + "/publication/researchproduct")
|
|
// .map(item -> OBJECT_MAPPER.readValue(item, ResearchProduct.class));
|
|
//
|
|
// org.apache.spark.sql.Dataset<ResearchProduct> researchProductDataset = spark
|
|
// .createDataset(researchProduct.rdd(), Encoders.bean(ResearchProduct.class));
|
|
//
|
|
// Assertions.assertEquals(1, researchProductDataset.filter((FilterFunction<ResearchProduct>) p -> p.getLocal_identifier().equalsIgnoreCase(Utils.getIdentifier(Prefixes.RESEARCH_PRODUCT, "50|DansKnawCris::0224aae28af558f21768dbc6439c7a95"))).count());
|
|
// ResearchProduct product = researchProductDataset.filter((FilterFunction<ResearchProduct>) p -> p.getLocal_identifier().equalsIgnoreCase(Utils.getIdentifier(Prefixes.RESEARCH_PRODUCT, "50|DansKnawCris::0224aae28af558f21768dbc6439c7a95"))).first();
|
|
// Assertions.assertEquals(2, product.getRelevant_organizations().size());
|
|
// Assertions.assertEquals(1, product.getFunding().size());
|
|
// Assertions.assertEquals(0, product.getRelated_products().size());
|
|
// Assertions.assertEquals(1, product.getContributions().size());
|
|
// Assertions.assertEquals(2, product.getManifestations().size());
|
|
//
|
|
// researchProductDataset.show(false);
|
|
//
|
|
//
|
|
|
|
}
|
|
}
|