sabeel
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

code formatting

This commit is contained in:
Claudio Atzori 2022-11-17 09:55:41 +01:00
parent ddff0e8999
commit 3dbc637d3e
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
dhp-workflows/dhp-dedup-openaire/src/test/java/eu/dnetlib/dhp/oa/dedup/SparkDedupPublicationTest.java
View File

@ -15,7 +15,6 @@ import java.nio.file.Paths;
import java.util.*; import java.util.*;
import java.util.stream.Collectors; import java.util.stream.Collectors;
import com.fasterxml.jackson.core.JsonProcessingException;
import org.apache.commons.io.FileUtils; import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
@ -32,6 +31,7 @@ import org.mockito.Mock;
import org.mockito.Mockito; import org.mockito.Mockito;
import org.mockito.junit.jupiter.MockitoExtension; import org.mockito.junit.jupiter.MockitoExtension;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.DeserializationFeature; import com.fasterxml.jackson.databind.DeserializationFeature;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.collect.Sets; import com.google.common.collect.Sets;
@ -299,17 +299,18 @@ public class SparkDedupPublicationTest implements Serializable {
assertEquals("Article", instance_cr.get().getInstancetype().getClassname()); assertEquals("Article", instance_cr.get().getInstancetype().getClassname());
} }
private void verifyRoot_case_2(Dataset<Publication> roots, Dataset<Publication> pubs) throws JsonProcessingException { private void verifyRoot_case_2(Dataset<Publication> roots, Dataset<Publication> pubs)
throws JsonProcessingException {
Publication root = roots Publication root = roots
.filter("id = '50|doi_dedup___::18aff3b55fb6876466a5d4bd82434885'") .filter("id = '50|doi_dedup___::18aff3b55fb6876466a5d4bd82434885'")
.first(); .first();
assertNotNull(root); assertNotNull(root);
Publication crossref_duplicate = pubs Publication crossref_duplicate = pubs
.filter("id = '50|doi_________::18aff3b55fb6876466a5d4bd82434885'") .filter("id = '50|doi_________::18aff3b55fb6876466a5d4bd82434885'")
.first(); .first();
//System.err.println(new ObjectMapper().writeValueAsString(root)); // System.err.println(new ObjectMapper().writeValueAsString(root));
assertEquals(crossref_duplicate.getJournal().getName(), root.getJournal().getName()); assertEquals(crossref_duplicate.getJournal().getName(), root.getJournal().getName());
assertEquals(crossref_duplicate.getJournal().getIssnOnline(), root.getJournal().getIssnOnline()); assertEquals(crossref_duplicate.getJournal().getIssnOnline(), root.getJournal().getIssnOnline());
@ -325,10 +326,10 @@ public class SparkDedupPublicationTest implements Serializable {
.collect(Collectors.toCollection(HashSet::new)); .collect(Collectors.toCollection(HashSet::new));
Set<String> root_cf = root Set<String> root_cf = root
.getCollectedfrom() .getCollectedfrom()
.stream() .stream()
.map(KeyValue::getValue) .map(KeyValue::getValue)
.collect(Collectors.toCollection(HashSet::new)); .collect(Collectors.toCollection(HashSet::new));
assertTrue(Sets.difference(root_cf, dups_cf).isEmpty()); assertTrue(Sets.difference(root_cf, dups_cf).isEmpty());
} }