summaryrefslogtreecommitdiff
path: root/corpus
diff options
context:
space:
mode:
Diffstat (limited to 'corpus')
-rwxr-xr-xcorpus/support/quote-norm.pl1
1 files changed, 1 insertions, 0 deletions
diff --git a/corpus/support/quote-norm.pl b/corpus/support/quote-norm.pl
index 0366fad5..3eee0666 100755
--- a/corpus/support/quote-norm.pl
+++ b/corpus/support/quote-norm.pl
@@ -40,6 +40,7 @@ while(<STDIN>) {
# Regularlize spaces:
s/\x{ad}//g; # soft hyphen
+ s/\x{200C}//g; # zero-width non-joiner
s/\x{a0}/ /g; # non-breaking space
s/\x{2009}/ /g; # thin space
s/\x{2028}/ /g; # "line separator"