From 885e0dd926a50212dbab9f583f1b72d162d94be5 Mon Sep 17 00:00:00 2001 From: Claudio Atzori Date: Tue, 26 Jan 2021 09:48:53 +0100 Subject: [PATCH] [Cleaning] filter authors not providing word characters in the fullname --- .../java/eu/dnetlib/dhp/oa/graph/clean/CleaningFunctions.java | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleaningFunctions.java b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleaningFunctions.java index 0d69a448e..db7d34ec9 100644 --- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleaningFunctions.java +++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleaningFunctions.java @@ -206,7 +206,8 @@ public class CleaningFunctions { .getAuthor() .stream() .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())); boolean nullRank = r