added one test to verify the dump for the datasources

This commit is contained in:
Miriam Baglioni 2020-07-29 18:27:46 +02:00
parent 86bab79512
commit ef1d8aef17
1 changed files with 30 additions and 5 deletions

View File

@ -6,6 +6,7 @@ import java.nio.file.Files;
import java.nio.file.Path; import java.nio.file.Path;
import java.util.HashMap; import java.util.HashMap;
import eu.dnetlib.dhp.schema.oaf.Datasource;
import org.apache.commons.io.FileUtils; import org.apache.commons.io.FileUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaRDD;
@ -24,7 +25,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.oaf.Organization; import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Project; import eu.dnetlib.dhp.schema.oaf.Project;
public class DumpOrganizationProjectTest { public class DumpOrganizationProjectDatasourceTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
@ -33,18 +34,18 @@ public class DumpOrganizationProjectTest {
private static Path workingDir; private static Path workingDir;
private static final Logger log = LoggerFactory private static final Logger log = LoggerFactory
.getLogger(DumpOrganizationProjectTest.class); .getLogger(DumpOrganizationProjectDatasourceTest.class);
private static HashMap<String, String> map = new HashMap<>(); private static HashMap<String, String> map = new HashMap<>();
@BeforeAll @BeforeAll
public static void beforeAll() throws IOException { public static void beforeAll() throws IOException {
workingDir = Files workingDir = Files
.createTempDirectory(DumpOrganizationProjectTest.class.getSimpleName()); .createTempDirectory(DumpOrganizationProjectDatasourceTest.class.getSimpleName());
log.info("using work dir {}", workingDir); log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf(); SparkConf conf = new SparkConf();
conf.setAppName(DumpOrganizationProjectTest.class.getSimpleName()); conf.setAppName(DumpOrganizationProjectDatasourceTest.class.getSimpleName());
conf.setMaster("local[*]"); conf.setMaster("local[*]");
conf.set("spark.driver.host", "localhost"); conf.set("spark.driver.host", "localhost");
@ -55,7 +56,7 @@ public class DumpOrganizationProjectTest {
spark = SparkSession spark = SparkSession
.builder() .builder()
.appName(DumpOrganizationProjectTest.class.getSimpleName()) .appName(DumpOrganizationProjectDatasourceTest.class.getSimpleName())
.config(conf) .config(conf)
.getOrCreate(); .getOrCreate();
} }
@ -118,4 +119,28 @@ public class DumpOrganizationProjectTest {
} }
@Test
public void dumpDatasourceTest(){
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/graph/datasource")
.getPath();
DumpGraphEntities dg = new DumpGraphEntities();
dg.run(false, sourcePath, workingDir.toString() + "/dump", Datasource.class, null);
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<eu.dnetlib.dhp.schema.dump.oaf.graph.Datasource> tmp = sc
.textFile(workingDir.toString() + "/dump")
.map(item -> OBJECT_MAPPER.readValue(item, eu.dnetlib.dhp.schema.dump.oaf.graph.Datasource.class));
org.apache.spark.sql.Dataset<eu.dnetlib.dhp.schema.dump.oaf.graph.Datasource> verificationDataset = spark
.createDataset(tmp.rdd(), Encoders.bean(eu.dnetlib.dhp.schema.dump.oaf.graph.Datasource.class));
Assertions.assertEquals(5, verificationDataset.count());
verificationDataset.foreach(o -> System.out.println(OBJECT_MAPPER.writeValueAsString(o)));
}
} }