antonis.lempesis
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 1
Code Issues Pull Requests Projects Releases Wiki Activity

[Cleaning] filter authors not providing word characters in the fullname

This commit is contained in:
Claudio Atzori 2021-01-26 09:48:53 +01:00
parent 2890511613
commit 885e0dd926
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleaningFunctions.java
View File

@ -206,7 +206,8 @@ public class CleaningFunctions {
.getAuthor() .getAuthor()
.stream() .stream()
.filter(a -> Objects.nonNull(a)) .filter(a -> Objects.nonNull(a))
.filter(a -> StringUtils.isNotBlank(StringUtils.trim(a.getFullname()))) .filter(a -> StringUtils.isNotBlank(a.getFullname()))
.filter(a -> StringUtils.isNotBlank(a.getFullname().replaceAll("[\\W]", "")))
.collect(Collectors.toList())); .collect(Collectors.toList()));
boolean nullRank = r boolean nullRank = r