D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

[orcidPropagatio] changed the test to include parameter and changed the values for the new resources

This commit is contained in:
Miriam Baglioni 2024-12-19 11:02:42 +01:00
parent 60cfaf119b
commit 345d69d11b
1 changed files with 13 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/OrcidPropagationJobTest.java
View File

@ -4,11 +4,19 @@ package eu.dnetlib.dhp.orcidtoresultfromsemrel;
import java.io.IOException; import java.io.IOException;
import java.nio.file.Files; import java.nio.file.Files;
import java.nio.file.Path; import java.nio.file.Path;
import java.util.Optional;
import java.util.logging.Filter;
import eu.dnetlib.dhp.common.enrichment.Constants;
import eu.dnetlib.dhp.schema.oaf.Author;
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;
import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.ForeachFunction;
import org.apache.spark.sql.Encoders; import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row; import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession; import org.apache.spark.sql.SparkSession;
@ -122,7 +130,8 @@ public class OrcidPropagationJobTest {
"-targetPath", "-targetPath",
workingDir.toString() + "/graph", workingDir.toString() + "/graph",
"-orcidPath", "", "-orcidPath", "",
"-workingDir", workingDir.toString() "-workingDir", workingDir.toString(),
"-matchingSource", "propagation"
}); });
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext()); final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
@ -131,7 +140,6 @@ public class OrcidPropagationJobTest {
.textFile(workingDir.toString() + "/graph/dataset") .textFile(workingDir.toString() + "/graph/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class)); .map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
// tmp.map(s -> new Gson().toJson(s)).foreach(s -> System.out.println(s));
Assertions.assertEquals(10, tmp.count()); Assertions.assertEquals(10, tmp.count());
@ -147,6 +155,7 @@ public class OrcidPropagationJobTest {
+ "where MyP.datainfo.inferenceprovenance = 'propagation'"; + "where MyP.datainfo.inferenceprovenance = 'propagation'";
org.apache.spark.sql.Dataset<Row> propagatedAuthors = spark.sql(query); org.apache.spark.sql.Dataset<Row> propagatedAuthors = spark.sql(query);
propagatedAuthors.show(false);
Assertions.assertEquals(1, propagatedAuthors.count()); Assertions.assertEquals(1, propagatedAuthors.count());
@ -156,12 +165,12 @@ public class OrcidPropagationJobTest {
propagatedAuthors propagatedAuthors
.filter( .filter(
"id = '50|dedup_wf_001::95b033c0c3961f6a1cdcd41a99a9632e' " "id = '50|dedup_wf_001::95b033c0c3961f6a1cdcd41a99a9632e' "
+ "and name = 'Vajinder' and surname = 'Kumar' and pidType = '" + + "and name = 'Nicole' and surname = 'Jung' and pidType = '" +
ModelConstants.ORCID_PENDING + "'") ModelConstants.ORCID_PENDING + "'")
.count()); .count());
Assertions.assertEquals(1, propagatedAuthors.filter("pid = '0000-0002-8825-3517'").count()); Assertions.assertEquals(1, propagatedAuthors.filter("pid = '0000-0001-9513-2468'").count());
} }
@Test @Test