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 | 445ba0b0ba94284d17c88a7e75f81c5d3c54a001 (patch) | |
| tree | 6f655d69d397089d7bc9e87d8cd104657d4c0967 /corpus/tokenize-anything.sh | |
| parent | 3a162d28033d1b9d5241e31f32978dba4eba6296 (diff) | |
| parent | 99538847039c06bdcc288e2c5dfcdb507ff879ca (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;}' |