forked from D-Net/dnet-hadoop
removed duplicated subjects
This commit is contained in:
parent
33dcf9964c
commit
18c9b95cb1
|
@ -254,6 +254,18 @@ public class RDFConverter {
|
|||
});
|
||||
});
|
||||
|
||||
dataciteProteins
|
||||
.stream()
|
||||
.filter(d -> (d.getSubjects() != null && !d.getSubjects().isEmpty()))
|
||||
.forEach(d -> {
|
||||
Map<String, DataciteProtein.Subject> cleanedSubjects = new HashMap<>();
|
||||
d.getSubjects().stream().forEach(s -> {
|
||||
cleanedSubjects.putIfAbsent(s.getValue(), s);
|
||||
});
|
||||
d.getSubjects().clear();
|
||||
d.setSubjects(cleanedSubjects.values().stream().collect(Collectors.toList()));
|
||||
});
|
||||
|
||||
dataciteProteins.forEach(d -> {
|
||||
DataciteProtein.Title title = new DataciteProtein.Title();
|
||||
title.setTitle(d.getId() + " - ".concat(mainTitles.get(0)));
|
||||
|
|
Loading…
Reference in New Issue