summaryrefslogtreecommitdiff
path: root/corpus/utf8-normalize.sh
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2015-01-19 14:39:14 +0100
committerPatrick Simianer <p@simianer.de>2015-01-19 14:39:14 +0100
commit0673fb55c6af8bc94c9f3e577c514160faf736d3 (patch)
treeff4edd0e1e816f4d412601689ab510b2d0aaccf7 /corpus/utf8-normalize.sh
parentcb9fb7088dde35881516c088db402abe747d49fa (diff)
parent1bce604809399a0adc581fb0102bff11decf3436 (diff)
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'corpus/utf8-normalize.sh')
-rwxr-xr-xcorpus/utf8-normalize.sh2
1 files changed, 1 insertions, 1 deletions
diff --git a/corpus/utf8-normalize.sh b/corpus/utf8-normalize.sh
index dcf8bc59..7c0db611 100755
--- a/corpus/utf8-normalize.sh
+++ b/corpus/utf8-normalize.sh
@@ -7,7 +7,7 @@
if which uconv > /dev/null
then
- CMD="uconv -f utf8 -t utf8 -x Any-NFKC --callback skip"
+ CMD="uconv -f utf8 -t utf8 -x Any-NFKC --callback skip --remove-signature"
else
echo "Cannot find ICU uconv (http://site.icu-project.org/) ... falling back to iconv. Normalization NOT taking place." 1>&2
CMD="iconv -f utf8 -t utf8 -c"