diff options
| author | Paul Baltescu <pauldb89@gmail.com> | 2013-11-23 17:33:47 +0000 |
|---|---|---|
| committer | Paul Baltescu <pauldb89@gmail.com> | 2013-11-23 17:33:47 +0000 |
| commit | 072c4bb1edde483b87b93bc6f4eec36fc8a21008 (patch) | |
| tree | 6ceaa6ae1e08df9e523282740b14f4857236297c /corpus/tokenize-anything.sh | |
| parent | 7e90b8ea10904f9b83f4e77e14c7396a3e6f7d5d (diff) | |
| parent | 9e80389b9763aa4f7f626ec71b561ccf6948d3ad (diff) | |
Merge branch 'master' of https://github.com/redpony/cdec
Diffstat (limited to 'corpus/tokenize-anything.sh')
| -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;}' |