forked from D-Net/dnet-hadoop
added a couple more invalid author names
This commit is contained in:
parent
3cad4a415d
commit
d070db4a32
|
@ -92,6 +92,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
|
|||
INVALID_AUTHOR_NAMES.add("null anonymous");
|
||||
INVALID_AUTHOR_NAMES.add("unbekannt");
|
||||
INVALID_AUTHOR_NAMES.add("unknown");
|
||||
INVALID_AUTHOR_NAMES.add("autor, Sin");
|
||||
INVALID_AUTHOR_NAMES.add("Desconocido / Inconnu,");
|
||||
|
||||
INVALID_URL_HOSTS.add("creativecommons.org");
|
||||
INVALID_URL_HOSTS.add("www.academia.edu");
|
||||
|
|
Loading…
Reference in New Issue