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 | cc6313b23cac25eb05976b6cf64f96faf1ed4163 (patch) | |
| tree | 3dc28060ad25b43773e875bea7388ab1cefcd927 /corpus/tokenize-anything.sh | |
| parent | 7990c750829af93f0a1e0fc14534582f52ee9e8c (diff) | |
| parent | f2fb69b10a897e8beb4e6e6d6cbb4327096235ef (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;}' |