diff options
| author | Chris Dyer <cdyer@allegro.clab.cs.cmu.edu> | 2013-03-08 22:45:06 -0500 |
|---|---|---|
| committer | Chris Dyer <cdyer@allegro.clab.cs.cmu.edu> | 2013-03-08 22:45:06 -0500 |
| commit | c3675cd0aae062446d7a5f5b7e91593b18c969f9 (patch) | |
| tree | 4ffa7196537a2e728f2a2ca3548d77f4c2def6b0 /corpus/tokenize-anything.sh | |
| parent | e419e52189ce8472bc5f5517796d00f0887affa7 (diff) | |
| parent | 7973046992b710a170a84888820ce76a9e4f2346 (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;}' |