diff options
| author | Patrick Simianer <p@simianer.de> | 2014-03-16 17:48:48 +0100 |
|---|---|---|
| committer | Patrick Simianer <p@simianer.de> | 2014-03-16 17:48:48 +0100 |
| commit | 5250fd67a4b8f242068cff87f0a6a4211f8b0fcf (patch) | |
| tree | f1401c1fd3eeae8671e59baf0d2169d1eb721cb7 /corpus/support/quote-norm.pl | |
| parent | 3eedf96b5a08b3e3414888d328c505814b84d8db (diff) | |
| parent | cc87bfed0697583b7c11243913254dde3c0047d4 (diff) | |
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'corpus/support/quote-norm.pl')
| -rwxr-xr-x | corpus/support/quote-norm.pl | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/corpus/support/quote-norm.pl b/corpus/support/quote-norm.pl index 33604027..0366fad5 100755 --- a/corpus/support/quote-norm.pl +++ b/corpus/support/quote-norm.pl @@ -39,6 +39,7 @@ while(<STDIN>) { s/&\#([0-9]+);/pack("U", $1)/ge; # Regularlize spaces: + s/\x{ad}//g; # soft hyphen s/\x{a0}/ /g; # non-breaking space s/\x{2009}/ /g; # thin space s/\x{2028}/ /g; # "line separator" |