[DUMP CSV] test and resources for the result dumps
This commit is contained in:
parent
66873c1744
commit
21599598ae
|
@ -1,9 +1,269 @@
|
|||
|
||||
package eu.dnetlib.dhp.oa.graph.dump.csv;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||
import org.apache.commons.io.FileUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.sql.Dataset;
|
||||
import org.apache.spark.sql.Row;
|
||||
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 java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
import java.util.HashMap;
|
||||
import java.util.Optional;
|
||||
|
||||
import static org.apache.commons.lang3.StringUtils.split;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 11/05/23
|
||||
*/
|
||||
public class DumpResultTest {
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
private static SparkSession spark;
|
||||
|
||||
private static Path workingDir;
|
||||
|
||||
private static final Logger log = LoggerFactory
|
||||
.getLogger(DumpResultTest.class);
|
||||
|
||||
private static HashMap<String, String> map = new HashMap<>();
|
||||
|
||||
@BeforeAll
|
||||
public static void beforeAll() throws IOException {
|
||||
workingDir = Files
|
||||
.createTempDirectory(DumpResultTest.class.getSimpleName());
|
||||
log.info("using work dir {}", workingDir);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
conf.setAppName(DumpResultTest.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(DumpResultTest.class.getSimpleName())
|
||||
.config(conf)
|
||||
.getOrCreate();
|
||||
}
|
||||
|
||||
@AfterAll
|
||||
public static void afterAll() throws IOException {
|
||||
FileUtils.deleteDirectory(workingDir.toFile());
|
||||
spark.stop();
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testDumpResult() throws Exception {
|
||||
|
||||
final String sourcePath = getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/csv/input/")
|
||||
.getPath();
|
||||
|
||||
spark.read().text(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/csv/working/resultIds")
|
||||
.getPath())
|
||||
.write()
|
||||
.text(workingDir.toString() + "/working/resultIds/");
|
||||
|
||||
SparkDumpResults.main(new String[] {
|
||||
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||
"-outputPath", workingDir.toString() + "/output",
|
||||
"-workingPath", workingDir.toString() + "/working",
|
||||
"-resultType", "publication",
|
||||
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Publication",
|
||||
"-sourcePath", sourcePath
|
||||
});
|
||||
|
||||
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
Dataset<Row> tmp = spark.read().option("header", "true").option("delimiter", Constants.SEP)
|
||||
.csv(workingDir.toString() + "/working/publication/result");
|
||||
|
||||
Assertions.assertEquals(3, tmp.count());
|
||||
Row row = tmp
|
||||
.where("id = '50|DansKnawCris::0224aae28af558f21768dbc6439c7a95'")
|
||||
.first();
|
||||
Assertions.assertEquals(ModelConstants.OPEN_ACCESS_RIGHT().getClassid(),row.getAs("accessright"));
|
||||
Assertions.assertEquals("FI" ,row.getAs("country"));
|
||||
Assertions.assertEquals("Lit.opg., bijl." ,row.getAs("description"));
|
||||
Assertions.assertEquals(3 ,split(row.getAs("keywords"), ", ").length);
|
||||
Assertions.assertTrue(row.getAs("keywords").toString().contains("archeologie"));
|
||||
Assertions.assertTrue(row.getAs("keywords").toString().contains("prospectie"));
|
||||
Assertions.assertTrue(row.getAs("keywords").toString().contains("archaeology"));
|
||||
Assertions.assertEquals("nl", row.getAs("language"));
|
||||
Assertions.assertEquals("2007-01-01", row.getAs("publication_date"));
|
||||
Assertions.assertEquals("FakePublisher1", row.getAs("publisher"));
|
||||
Assertions.assertEquals("Inventariserend veldonderzoek d.m.v. boringen (karterende fase) : Raadhuisstraat te Dirkshorn, gemeente Harenkarspel", row.getAs("title"));
|
||||
Assertions.assertEquals("publication", row.getAs("type"));
|
||||
|
||||
row = tmp
|
||||
.where("id = '50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9'")
|
||||
.first();
|
||||
Assertions.assertEquals(ModelConstants.OPEN_ACCESS_RIGHT().getClassid(),row.getAs("accessright"));
|
||||
Assertions.assertEquals(2 ,split(row.getAs("country"), ", ").length);
|
||||
Assertions.assertNull(row.getAs("description"));
|
||||
Assertions.assertEquals(2 ,split(row.getAs("keywords"), ", ").length);
|
||||
Assertions.assertTrue(row.getAs("keywords").toString().contains("archeologie"));
|
||||
Assertions.assertTrue(row.getAs("keywords").toString().contains("archaeology"));
|
||||
Assertions.assertEquals("UNKNOWN", row.getAs("language"));
|
||||
Assertions.assertNull( row.getAs("publication_date"));
|
||||
Assertions.assertNull( row.getAs("publisher"));
|
||||
Assertions.assertEquals("None", row.getAs("title"));
|
||||
Assertions.assertEquals("publication", row.getAs("type"));
|
||||
|
||||
row = tmp
|
||||
.where("id = '50|DansKnawCris::26780065282e607306372abd0d808245'")
|
||||
.first();
|
||||
Assertions.assertEquals(ModelConstants.OPEN_ACCESS_RIGHT().getClassid(),row.getAs("accessright"));
|
||||
Assertions.assertNull(row.getAs("country"));
|
||||
Assertions.assertNull(row.getAs("description"));
|
||||
Assertions.assertEquals(2 ,split(row.getAs("keywords"), ", ").length);
|
||||
Assertions.assertTrue(row.getAs("keywords").toString().contains("archeologie"));
|
||||
Assertions.assertTrue(row.getAs("keywords").toString().contains("archaeology"));
|
||||
Assertions.assertEquals("UNKNOWN", row.getAs("language"));
|
||||
Assertions.assertNull( row.getAs("publication_date"));
|
||||
Assertions.assertNull( row.getAs("publisher"));
|
||||
Assertions.assertEquals("None", row.getAs("title"));
|
||||
Assertions.assertEquals("publication", row.getAs("type"));
|
||||
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testDumpAuthor() throws Exception {
|
||||
|
||||
final String sourcePath = getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/csv/input/")
|
||||
.getPath();
|
||||
|
||||
spark.read().text(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/csv/working/resultIds")
|
||||
.getPath())
|
||||
.write()
|
||||
.text(workingDir.toString() + "/working/resultIds/");
|
||||
|
||||
SparkDumpResults.main(new String[] {
|
||||
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||
"-outputPath", workingDir.toString() + "/output",
|
||||
"-workingPath", workingDir.toString() + "/working",
|
||||
"-resultType", "publication",
|
||||
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Publication",
|
||||
"-sourcePath", sourcePath
|
||||
});
|
||||
|
||||
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
Dataset<Row> tmp = spark.read().option("header", "true").option("delimiter", Constants.SEP)
|
||||
.csv(workingDir.toString() + "/working/publication/author");
|
||||
|
||||
Assertions.assertEquals(5, tmp.count());
|
||||
|
||||
Assertions.assertEquals(1,tmp.where("firstName == 'Maryam'").count());
|
||||
|
||||
Assertions.assertEquals(DHPUtils.md5("50|DansKnawCris::0224aae28af558f21768dbc6439c7a951"),tmp.where("firstName == 'Maryam'").first().getAs("id"));
|
||||
Assertions.assertEquals(DHPUtils.md5("0000-0003-2914-2734"),tmp.where("firstName == 'Michael'").first().getAs("id"));
|
||||
Assertions.assertEquals(DHPUtils.md5("50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d92"),tmp.where("firstName == 'Mikhail'").first().getAs("id"));
|
||||
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testDumpResultAuthorRelations() throws Exception {
|
||||
|
||||
final String sourcePath = getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/csv/input/")
|
||||
.getPath();
|
||||
|
||||
spark.read().text(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/csv/working/resultIds")
|
||||
.getPath())
|
||||
.write()
|
||||
.text(workingDir.toString() + "/working/resultIds/");
|
||||
|
||||
SparkDumpResults.main(new String[] {
|
||||
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||
"-outputPath", workingDir.toString() + "/output",
|
||||
"-workingPath", workingDir.toString() + "/working",
|
||||
"-resultType", "publication",
|
||||
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Publication",
|
||||
"-sourcePath", sourcePath
|
||||
});
|
||||
|
||||
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
Dataset<Row> tmp = spark.read().option("header", "true").option("delimiter", Constants.SEP)
|
||||
.csv(workingDir.toString() + "/working/publication/result_author");
|
||||
|
||||
Assertions.assertEquals(6, tmp.count());
|
||||
|
||||
Assertions.assertEquals(2, tmp.where("author_id == '" + DHPUtils.md5("0000-0003-2914-2734") + "'").count());
|
||||
Assertions.assertEquals(1, tmp.where("author_id == '" + DHPUtils.md5("0000-0003-2914-2734") + "'")
|
||||
.where("result_id == '50|DansKnawCris::0224aae28af558f21768dbc6439c7a95'").count());
|
||||
Assertions.assertEquals(1, tmp.where("author_id == '" + DHPUtils.md5("0000-0003-2914-2734") + "'")
|
||||
.where("result_id == '50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9'").count());
|
||||
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testDumpResultPid() throws Exception {
|
||||
|
||||
final String sourcePath = getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/csv/input/")
|
||||
.getPath();
|
||||
|
||||
spark.read().text(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/csv/working/resultIds")
|
||||
.getPath())
|
||||
.write()
|
||||
.text(workingDir.toString() + "/working/resultIds/");
|
||||
|
||||
SparkDumpResults.main(new String[] {
|
||||
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||
"-outputPath", workingDir.toString() + "/output",
|
||||
"-workingPath", workingDir.toString() + "/working",
|
||||
"-resultType", "publication",
|
||||
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Publication",
|
||||
"-sourcePath", sourcePath
|
||||
});
|
||||
|
||||
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
Dataset<Row> tmp = spark.read().option("header", "true").option("delimiter", Constants.SEP)
|
||||
.csv(workingDir.toString() + "/working/publication/result_pid");
|
||||
|
||||
tmp.show(false);
|
||||
Assertions.assertEquals(4, tmp.count());
|
||||
|
||||
Assertions.assertEquals(2, tmp.where("result_id == '50|DansKnawCris::0224aae28af558f21768dbc6439c7a95'").count());
|
||||
Assertions.assertEquals("10.1023/fakedoi", tmp.where("result_id == '50|DansKnawCris::0224aae28af558f21768dbc6439c7a95' and type == 'doi'").first().getAs("pid"));
|
||||
|
||||
|
||||
}
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue