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

changed due to changes in the model

This commit is contained in:
Miriam Baglioni 2020-07-29 17:08:02 +02:00
parent d0ff2a56fb
commit de2ebb467e
1 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/PrepareResultProjectJobTest.java
View File

@ -6,10 +6,12 @@ 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.oa.graph.dump.community.ResultProject;
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.sql.Dataset;
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;
@ -22,6 +24,8 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject;
public class PrepareResultProjectJobTest { public class PrepareResultProjectJobTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
@ -77,7 +81,6 @@ public class PrepareResultProjectJobTest {
"-sourcePath", sourcePath "-sourcePath", sourcePath
}); });
// dumpCommunityProducts.exec(MOCK_IS_LOOK_UP_URL,Boolean.FALSE, workingDir.toString()+"/dataset",sourcePath,"eu.dnetlib.dhp.schema.oaf.Dataset","eu.dnetlib.dhp.schema.dump.oaf.Dataset");
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext()); final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
@ -105,8 +108,6 @@ public class PrepareResultProjectJobTest {
"-sourcePath", sourcePath "-sourcePath", sourcePath
}); });
// dumpCommunityProducts.exec(MOCK_IS_LOOK_UP_URL,Boolean.FALSE, workingDir.toString()+"/dataset",sourcePath,"eu.dnetlib.dhp.schema.oaf.Dataset","eu.dnetlib.dhp.schema.dump.oaf.Dataset");
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext()); final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<ResultProject> tmp = sc JavaRDD<ResultProject> tmp = sc
@ -123,6 +124,16 @@ public class PrepareResultProjectJobTest {
1, 1,
verificationDataset.filter("resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb'").count()); verificationDataset.filter("resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb'").count());
verificationDataset.createOrReplaceTempView("table");
Dataset<Row> check = spark.sql("Select projList.provenance.provenance " +
"from table " +
"lateral view explode (projectsList) pl as projList");
Assertions.assertEquals(1, check.filter("provenance = 'sysimport:crosswalk:entityregistry'").count());
verificationDataset.show(false);
} }
@Test @Test
@ -160,7 +171,7 @@ public class PrepareResultProjectJobTest {
verificationDataset.createOrReplaceTempView("dataset"); verificationDataset.createOrReplaceTempView("dataset");
String query = "select resultId, MyT.id project , MyT.title title, MyT.acronym acronym " String query = "select resultId, MyT.id project , MyT.title title, MyT.acronym acronym , MyT.provenance.provenance provenance "
+ "from dataset " + "from dataset "
+ "lateral view explode(projectsList) p as MyT "; + "lateral view explode(projectsList) p as MyT ";
@ -218,7 +229,8 @@ public class PrepareResultProjectJobTest {
"project = '40|aka_________::03376222b28a3aebf2730ac514818d04' and resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb'") "project = '40|aka_________::03376222b28a3aebf2730ac514818d04' and resultId = '50|dedup_wf_001::e4805d005bfab0cd39a1642cbf477fdb'")
.count()); .count());
resultExplodedProvenance.show(false); Assertions.assertEquals(3, resultExplodedProvenance.filter("provenance = 'sysimport:crosswalk:entityregistry'").count());
} }
} }