diff options
| author | Chris Dyer <cdyer@Chriss-MacBook-Air.local> | 2013-11-11 16:12:39 -0500 |
|---|---|---|
| committer | Chris Dyer <cdyer@Chriss-MacBook-Air.local> | 2013-11-11 16:12:39 -0500 |
| commit | 8a24bb77bc2e9fd17a6f6529a2942cde96a6af49 (patch) | |
| tree | ad97934518c68897291e43659eb141c0811015ca /corpus | |
| parent | ae282ff1c3b9669496af3308e0f7889658f564cc (diff) | |
error on new macs
Diffstat (limited to 'corpus')
| -rwxr-xr-x | corpus/tokenize-anything.sh | 4 |
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;}' |