[stats wf] indicators across stats dbs & updates in the org ids #248

Closed
dimitris.pierrakos wants to merge 1742 commits from beta into beta2master_sept_2022
2 changed files with 118 additions and 112 deletions
Showing only changes of commit 06a95daf60 - Show all commits

View File

@ -93,13 +93,9 @@ public class SparkEoscBulkTag implements Serializable {
String datasourceMapPath, String datasourceMapPath,
Class<R> resultClazz) { Class<R> resultClazz) {
List<String> hostedByList = readPath(spark, datasourceMapPath, DatasourceMaster.class) List<String> hostedByList = readPath(spark, datasourceMapPath, DatasourceMaster.class)
.map((MapFunction<DatasourceMaster, String>) dm -> dm.getMaster(), Encoders.STRING()) .map((MapFunction<DatasourceMaster, String>) dm -> dm.getMaster(), Encoders.STRING())
.collectAsList(); .collectAsList();
readPath(spark, inputPath, resultClazz) readPath(spark, inputPath, resultClazz)
.map(patchResult(), Encoders.bean(resultClazz)) .map(patchResult(), Encoders.bean(resultClazz))

View File

@ -1,16 +1,11 @@
package eu.dnetlib.dhp.bulktag; package eu.dnetlib.dhp.bulktag;
/**
* @author miriam.baglioni
* @Date 22/07/22
*/
import com.fasterxml.jackson.databind.ObjectMapper; import java.io.IOException;
import eu.dnetlib.dhp.bulktag.eosc.SparkEoscBulkTag; import java.nio.file.Files;
import eu.dnetlib.dhp.schema.oaf.Dataset; import java.nio.file.Path;
import eu.dnetlib.dhp.schema.oaf.OtherResearchProduct; import java.util.List;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
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;
@ -26,10 +21,17 @@ import org.junit.jupiter.api.Test;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import java.io.IOException; /**
import java.nio.file.Files; * @author miriam.baglioni
import java.nio.file.Path; * @Date 22/07/22
import java.util.List; */
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.bulktag.eosc.SparkEoscBulkTag;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import eu.dnetlib.dhp.schema.oaf.OtherResearchProduct;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
//"50|475c1990cbb2::0fecfb874d9395aa69d2f4d7cd1acbea" has instance hostedby eosc //"50|475c1990cbb2::0fecfb874d9395aa69d2f4d7cd1acbea" has instance hostedby eosc
//"50|475c1990cbb2::3185cd5d8a2b0a06bb9b23ef11748eb1" has instance hostedby eosc //"50|475c1990cbb2::3185cd5d8a2b0a06bb9b23ef11748eb1" has instance hostedby eosc
@ -37,116 +39,124 @@ import java.util.List;
//"50|475c1990cbb2::3894c94123e96df8a21249957cf160cb" has EoscTag //"50|475c1990cbb2::3894c94123e96df8a21249957cf160cb" has EoscTag
public class EOSCContextTaggingTest { public class EOSCContextTaggingTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static SparkSession spark; private static SparkSession spark;
private static Path workingDir; private static Path workingDir;
private static final Logger log = LoggerFactory.getLogger(EOSCContextTaggingTest.class); private static final Logger log = LoggerFactory.getLogger(EOSCContextTaggingTest.class);
@BeforeAll @BeforeAll
public static void beforeAll() throws IOException { public static void beforeAll() throws IOException {
workingDir = Files.createTempDirectory(EOSCContextTaggingTest.class.getSimpleName()); workingDir = Files.createTempDirectory(EOSCContextTaggingTest.class.getSimpleName());
log.info("using work dir {}", workingDir); log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf(); SparkConf conf = new SparkConf();
conf.setAppName(EOSCContextTaggingTest.class.getSimpleName()); conf.setAppName(EOSCContextTaggingTest.class.getSimpleName());
conf.setMaster("local[*]"); conf.setMaster("local[*]");
conf.set("spark.driver.host", "localhost"); conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true"); conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false"); conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.toString()); conf.set("spark.sql.warehouse.dir", workingDir.toString());
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString()); conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
spark = SparkSession spark = SparkSession
.builder() .builder()
.appName(EOSCTagJobTest.class.getSimpleName()) .appName(EOSCTagJobTest.class.getSimpleName())
.config(conf) .config(conf)
.getOrCreate(); .getOrCreate();
} }
@AfterAll @AfterAll
public static void afterAll() throws IOException { public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile()); FileUtils.deleteDirectory(workingDir.toFile());
spark.stop(); spark.stop();
} }
@Test @Test
void EoscContextTagTest() throws Exception { void EoscContextTagTest() throws Exception {
spark spark
.read() .read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/bulktag/eosc/dataset/dataset_10.json").getPath()) .textFile(getClass().getResource("/eu/dnetlib/dhp/bulktag/eosc/dataset/dataset_10.json").getPath())
.map( .map(
(MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class), (MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class),
Encoders.bean(Dataset.class)) Encoders.bean(Dataset.class))
.write() .write()
.mode(SaveMode.Overwrite) .mode(SaveMode.Overwrite)
.option("compression", "gzip") .option("compression", "gzip")
.json(workingDir.toString() + "/input/dataset"); .json(workingDir.toString() + "/input/dataset");
SparkEoscBulkTag
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-sourcePath",
workingDir.toString() + "/input/dataset",
"-workingPath", workingDir.toString() + "/working/dataset",
"-datasourceMapPath",
getClass()
.getResource("/eu/dnetlib/dhp/bulktag/eosc/datasourceMasterAssociation/datasourceMaster")
.getPath(),
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Dataset"
});
SparkEoscBulkTag final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-sourcePath",
workingDir.toString() + "/input/dataset",
"-workingPath", workingDir.toString() + "/working/dataset",
"-datasourceMapPath", getClass().getResource("/eu/dnetlib/dhp/bulktag/eosc/datasourceMasterAssociation/datasourceMaster").getPath(),
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Dataset"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext()); JavaRDD<Dataset> tmp = sc
.textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
JavaRDD<Dataset> tmp = sc Assertions.assertEquals(10, tmp.count());
.textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
Assertions.assertEquals(10, tmp.count()); Assertions
.assertEquals(
4,
tmp
.filter(
s -> s.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
.count());
Assertions Assertions
.assertEquals( .assertEquals(
4, 1,
tmp tmp
.filter( .filter(
s -> s.getContext().stream().anyMatch(c -> c.getId().equals("eosc"))) d -> d.getId().equals("50|475c1990cbb2::0fecfb874d9395aa69d2f4d7cd1acbea")
.count()); &&
d.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
.count());
Assertions
.assertEquals(
1,
tmp
.filter(
d -> d.getId().equals("50|475c1990cbb2::3185cd5d8a2b0a06bb9b23ef11748eb1")
&&
d.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
.count());
Assertions Assertions
.assertEquals(1, .assertEquals(
tmp 1,
.filter(d -> d.getId().equals("50|475c1990cbb2::0fecfb874d9395aa69d2f4d7cd1acbea") tmp
&& .filter(
d.getContext().stream().anyMatch(c -> c.getId().equals("eosc"))).count() d -> d.getId().equals("50|475c1990cbb2::3894c94123e96df8a21249957cf160cb")
); &&
Assertions d.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
.assertEquals(1, .count());
tmp
.filter(d -> d.getId().equals("50|475c1990cbb2::3185cd5d8a2b0a06bb9b23ef11748eb1")
&&
d.getContext().stream().anyMatch(c -> c.getId().equals("eosc"))).count()
);
Assertions
.assertEquals(1,
tmp
.filter(d -> d.getId().equals("50|475c1990cbb2::3894c94123e96df8a21249957cf160cb")
&&
d.getContext().stream().anyMatch(c -> c.getId().equals("eosc"))).count()
);
Assertions
.assertEquals(1,
tmp
.filter(d -> d.getId().equals("50|475c1990cbb2::3894c94123e96df8a21249957cf160cb")
&&
d.getContext().stream().anyMatch(c -> c.getId().equals("eosc"))).count()
);
}
Assertions
.assertEquals(
1,
tmp
.filter(
d -> d.getId().equals("50|475c1990cbb2::3894c94123e96df8a21249957cf160cb")
&&
d.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
.count());
}
} }