summaryrefslogtreecommitdiff
path: root/corpus/tokenize-anything.sh
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2014-10-13 19:03:48 +0100
committerPatrick Simianer <p@simianer.de>2014-10-13 19:03:48 +0100
commitcb9fb7088dde35881516c088db402abe747d49fa (patch)
treea91e4935a7941f1b261f76d88ab41fa3078a1891 /corpus/tokenize-anything.sh
parent0a00e57e921c8eca8e02364db7d2e6607bfdcebc (diff)
parentb1ed81ef3216b212295afa76c5d20a56fb647204 (diff)
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'corpus/tokenize-anything.sh')
-rwxr-xr-xcorpus/tokenize-anything.sh7
1 files changed, 7 insertions, 0 deletions
diff --git a/corpus/tokenize-anything.sh b/corpus/tokenize-anything.sh
index bca954d1..c580e88b 100755
--- a/corpus/tokenize-anything.sh
+++ b/corpus/tokenize-anything.sh
@@ -7,6 +7,13 @@ if [[ $# == 1 && $1 == '-u' ]] ; then
NORMARGS="--batchline"
SEDFLAGS="-u"
else
+ if [[ $# != 0 ]] ; then
+ echo Usage: `basename $0` [-u] \< file.in \> file.out 1>&2
+ echo 1>&2
+ echo Tokenizes text in a reasonable way in most languages. 1>&2
+ echo 1>&2
+ exit 1
+ fi
NORMARGS=""
SEDFLAGS=""
fi