D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 10 Projects 2 Releases 2 Wiki Activity

unit test for the preparation of the relations

This commit is contained in:
Claudio Atzori 2020-07-02 12:42:13 +02:00
parent ed1c7e5d75
commit d380b85246
1 changed files with 18 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/PrepareRelationsJobTest.java
View File

@ -1,9 +1,10 @@
package eu.dnetlib.dhp.oa.provision; package eu.dnetlib.dhp.oa.provision;
import com.fasterxml.jackson.databind.ObjectMapper; import java.io.IOException;
import eu.dnetlib.dhp.oa.provision.model.ProvisionModelSupport; import java.nio.file.Files;
import eu.dnetlib.dhp.schema.oaf.Relation; import java.nio.file.Path;
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.function.FilterFunction; import org.apache.spark.api.java.function.FilterFunction;
@ -19,9 +20,10 @@ import org.junit.jupiter.api.io.TempDir;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import java.io.IOException; import com.fasterxml.jackson.databind.ObjectMapper;
import java.nio.file.Files;
import java.nio.file.Path; import eu.dnetlib.dhp.oa.provision.model.ProvisionModelSupport;
import eu.dnetlib.dhp.schema.oaf.Relation;
public class PrepareRelationsJobTest { public class PrepareRelationsJobTest {
@ -74,14 +76,19 @@ public class PrepareRelationsJobTest {
"-maxRelations", String.valueOf(maxRelations) "-maxRelations", String.valueOf(maxRelations)
}); });
Dataset<Relation> out = spark.read() Dataset<Relation> out = spark
.read()
.parquet(testPath.toString()) .parquet(testPath.toString())
.as(Encoders.bean(Relation.class)) .as(Encoders.bean(Relation.class))
.cache(); .cache();
Assertions.assertEquals(10, out.count()); Assertions.assertEquals(10, out.count());
Dataset<Row> freq = out.toDF().cube(SUBRELTYPE).count().filter((FilterFunction<Row>) value -> !value.isNullAt(0)); Dataset<Row> freq = out
.toDF()
.cube(SUBRELTYPE)
.count()
.filter((FilterFunction<Row>) value -> !value.isNullAt(0));
long outcome = freq.filter(freq.col(SUBRELTYPE).equalTo(OUTCOME)).collectAsList().get(0).getAs("count"); long outcome = freq.filter(freq.col(SUBRELTYPE).equalTo(OUTCOME)).collectAsList().get(0).getAs("count");
long supplement = freq.filter(freq.col(SUBRELTYPE).equalTo(SUPPLEMENT)).collectAsList().get(0).getAs("count"); long supplement = freq.filter(freq.col(SUBRELTYPE).equalTo(SUPPLEMENT)).collectAsList().get(0).getAs("count");