diff options
| author | Patrick Simianer <p@simianer.de> | 2013-03-15 11:39:18 +0100 |
|---|---|---|
| committer | Patrick Simianer <p@simianer.de> | 2013-03-15 11:39:18 +0100 |
| commit | 3d8aa307d233f58cfe9ddcc616a8297551a738e3 (patch) | |
| tree | b9556fe62c7ac0d7b48d92481acdd06a546b1dc2 /corpus/tokenize-anything.sh | |
| parent | cf67d34738e1487f75739dc1e027b1864a06513b (diff) | |
| parent | 9f1d72fa4dc231eb8cdb737becfc10452b5daef4 (diff) | |
Merge remote-tracking branch 'upstream/master'
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;}' |