diff options
Diffstat (limited to 'corpus')
| -rwxr-xr-x | corpus/tokenize-anything.sh | 7 |
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 |