pispis
/
dnet-hadoop
forked from antonis.lempesis/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

code formatting

This commit is contained in:
Claudio Atzori 2020-12-22 14:59:03 +01:00
parent 7bfc35df5e
commit d8b5f43a7e
2 changed files with 73 additions and 72 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/AuthorMerger.java
View File

@ -73,7 +73,7 @@ public class AuthorMerger {
if (base == null || enrich == null)
return;
//<pidComparableString, Author> (if an Author has more than 1 pid, it appears 2 times in the list)
// <pidComparableString, Author> (if an Author has more than 1 pid, it appears 2 times in the list)
final Map<String, Author> basePidAuthorMap = base
.stream()
.filter(a -> a.getPid() != null && a.getPid().size() > 0)
@ -84,7 +84,7 @@ public class AuthorMerger {
.map(p -> new Tuple2<>(pidToComparableString(p), a)))
.collect(Collectors.toMap(Tuple2::_1, Tuple2::_2, (x1, x2) -> x1));
//<pid, Author> (list of pid that are missing in the other list)
// <pid, Author> (list of pid that are missing in the other list)
final List<Tuple2<StructuredProperty, Author>> pidToEnrich = enrich
.stream()
.filter(a -> a.getPid() != null && a.getPid().size() > 0)
@ -96,7 +96,6 @@ public class AuthorMerger {
.map(p -> new Tuple2<>(p, a)))
.collect(Collectors.toList());
pidToEnrich
.forEach(
a -> {

140
dhp-common/src/test/java/eu/dnetlib/dhp/oa/merge/AuthorMergerTest.java
View File

@ -1,14 +1,5 @@
package eu.dnetlib.dhp.oa.merge;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.pace.util.MapDocumentUtil;
import org.codehaus.jackson.map.ObjectMapper;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import scala.Tuple2;
package eu.dnetlib.dhp.oa.merge;
import java.io.BufferedReader;
import java.io.FileReader;
@ -18,80 +9,91 @@ import java.util.ArrayList;
import java.util.List;
import java.util.stream.Collectors;
import org.codehaus.jackson.map.ObjectMapper;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.pace.util.MapDocumentUtil;
import scala.Tuple2;
public class AuthorMergerTest {
String publicationsBasePath;
String publicationsBasePath;
List<List<Author>> authors;
List<List<Author>> authors;
@BeforeEach
public void setUp() throws Exception {
@BeforeEach
public void setUp() throws Exception {
publicationsBasePath = Paths
.get(AuthorMergerTest.class.getResource("/eu/dnetlib/dhp/oa/merge").toURI())
.toFile()
.getAbsolutePath();
publicationsBasePath = Paths
.get(AuthorMergerTest.class.getResource("/eu/dnetlib/dhp/oa/merge").toURI())
.toFile()
.getAbsolutePath();
authors =
readSample(publicationsBasePath + "/publications_with_authors.json", Publication.class)
.stream()
.map(p -> p._2().getAuthor()).collect(Collectors.toList());
authors = readSample(publicationsBasePath + "/publications_with_authors.json", Publication.class)
.stream()
.map(p -> p._2().getAuthor())
.collect(Collectors.toList());
}
}
@Test
public void mergeTest() { //used in the dedup: threshold set to 0.95
@Test
public void mergeTest() { // used in the dedup: threshold set to 0.95
for (List<Author> authors1: authors){
System.out.println("List " + (authors.indexOf(authors1)+1));
for (Author author: authors1){
System.out.println(authorToString(author));
}
}
for (List<Author> authors1 : authors) {
System.out.println("List " + (authors.indexOf(authors1) + 1));
for (Author author : authors1) {
System.out.println(authorToString(author));
}
}
List<Author> merge = AuthorMerger.merge(authors);
List<Author> merge = AuthorMerger.merge(authors);
System.out.println("Merge ");
for (Author author: merge) {
System.out.println(authorToString(author));
}
System.out.println("Merge ");
for (Author author : merge) {
System.out.println(authorToString(author));
}
Assertions.assertEquals(7, merge.size());
Assertions.assertEquals(7, merge.size());
}
}
public <T> List<Tuple2<String, T>> readSample(String path, Class<T> clazz) {
List<Tuple2<String, T>> res = new ArrayList<>();
BufferedReader reader;
try {
reader = new BufferedReader(new FileReader(path));
String line = reader.readLine();
while (line != null) {
res
.add(
new Tuple2<>(
MapDocumentUtil.getJPathString("$.id", line),
new ObjectMapper().readValue(line, clazz)));
// read next line
line = reader.readLine();
}
reader.close();
} catch (IOException e) {
e.printStackTrace();
}
public <T> List<Tuple2<String, T>> readSample(String path, Class<T> clazz) {
List<Tuple2<String, T>> res = new ArrayList<>();
BufferedReader reader;
try {
reader = new BufferedReader(new FileReader(path));
String line = reader.readLine();
while (line != null) {
res
.add(
new Tuple2<>(
MapDocumentUtil.getJPathString("$.id", line),
new ObjectMapper().readValue(line, clazz)));
// read next line
line = reader.readLine();
}
reader.close();
} catch (IOException e) {
e.printStackTrace();
}
return res;
}
return res;
}
public String authorToString(Author a){
public String authorToString(Author a) {
String print = "Fullname = ";
print += a.getFullname() + " pid = [";
if (a.getPid() != null)
for (StructuredProperty sp : a.getPid()) {
print += sp.toComparableString() + " ";
}
print += "]";
return print;
}
String print = "Fullname = ";
print += a.getFullname() + " pid = [";
if (a.getPid() != null)
for (StructuredProperty sp : a.getPid()) {
print += sp.toComparableString() + " ";
}
print += "]";
return print;
}
}