diff options
| author | Paul Baltescu <pauldb89@gmail.com> | 2013-04-24 17:18:10 +0100 |
|---|---|---|
| committer | Paul Baltescu <pauldb89@gmail.com> | 2013-04-24 17:18:10 +0100 |
| commit | ba206aaac1d95e76126443c9e7ccc5941e879849 (patch) | |
| tree | 13a918da3f3983fd8e4cb74e7cdc3f5e1fc01cd1 /corpus/tokenize-anything.sh | |
| parent | c2aede0f19b7a5e43581768b8c4fbfae8b92c68c (diff) | |
| parent | db960a8bba81df3217660ec5a96d73e0d6baa01b (diff) | |
Merge branch 'master' of https://github.com/redpony/cdec
Diffstat (limited to 'corpus/tokenize-anything.sh')
| -rwxr-xr-x | corpus/tokenize-anything.sh | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/corpus/tokenize-anything.sh b/corpus/tokenize-anything.sh index 1a24193d..028992cf 100755 --- a/corpus/tokenize-anything.sh +++ b/corpus/tokenize-anything.sh @@ -9,5 +9,5 @@ $SUPPORT/utf8-normalize.sh | sed -e 's/ al - / al-/g' | $SUPPORT/fix-contract.pl | sed -e 's/^ //' | sed -e 's/ $//' | - perl -e 'while(<>){s/(\d+)(\.+)$/$1 ./;print;}' + perl -e 'while(<>){s/(\d+)(\.+)$/$1 ./; s/(\d+)(\.+) \|\|\|/$1 . |||/; print;}' |