diff options
| author | Chris Dyer <cdyer@allegro.clab.cs.cmu.edu> | 2012-12-05 20:27:30 -0500 |
|---|---|---|
| committer | Chris Dyer <cdyer@allegro.clab.cs.cmu.edu> | 2012-12-05 20:27:30 -0500 |
| commit | 8bc9e5d9cfe634191c83bd735af4571525133cfe (patch) | |
| tree | 9cedab6a92b0e8e7bac0a930f23ba0850b152aa7 /corpus/support/quote-norm.pl | |
| parent | d7b60765395a4fe6da23992f45afd18dfc093aeb (diff) | |
remove logging, you should be using pv
Diffstat (limited to 'corpus/support/quote-norm.pl')
| -rwxr-xr-x | corpus/support/quote-norm.pl | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/corpus/support/quote-norm.pl b/corpus/support/quote-norm.pl index 0c5b9c26..72b0064d 100755 --- a/corpus/support/quote-norm.pl +++ b/corpus/support/quote-norm.pl @@ -18,13 +18,18 @@ while(<STDIN>) { s/(\W)(euro?)(\d*\.\d+|\d+)/$1EUR $3/gi; s/&\s*#45\s*;\s*&\s*#45\s*;/--/g; s/&\s*#45\s*;/--/g; + s/�c/--/g; s/ ,,/ "/g; s/``/"/g; s/''/"/g; + s/[「」]/"/g; s/〃/"/g; s/¨/"/g; s/¡/ ¡ /g; s/¿/ ¿ /g; + # â<U+0080><U+0099> + s/â(\x{80}\x{99}|\x{80}\x{98})/'/g; + s/â(\x{80}\x{9c}|\x{80}\x{9d})/"/g; s/ˇ/'/g; s/´/'/g; s/`/'/g; @@ -39,7 +44,7 @@ while(<STDIN>) { s/»/"/g; tr/！-～/!-~/; s/、/,/g; - s/。/./g; + # s/。/./g; s/…/.../g; s/―/--/g; s/–/--/g; |