summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rwxr-xr-xcorpus/tokenize-anything.sh4
1 files changed, 2 insertions, 2 deletions
diff --git a/corpus/tokenize-anything.sh b/corpus/tokenize-anything.sh
index fb038717..c7adfa61 100755
--- a/corpus/tokenize-anything.sh
+++ b/corpus/tokenize-anything.sh
@@ -12,8 +12,8 @@ fi
$SUPPORT/utf8-normalize.sh $NORMARGS |
$SUPPORT/quote-norm.pl |
$SUPPORT/tokenizer.pl |
- sed -u -e 's/ al - / al-/g' |
+ sed -e 's/ al - / al-/g' |
$SUPPORT/fix-contract.pl |
- sed -u -e 's/^ //' | sed -u -e 's/ $//' |
+ sed -e 's/^ //' | sed -e 's/ $//' |
perl -e '$|++; while(<>){s/(\d+)(\.+)$/$1 ./; s/(\d+)(\.+) \|\|\|/$1 . |||/; print;}'