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 | 4f191a593918c7889f2c27cd9f596bec591bf736 (patch) | |
tree | 07635cd6e1544c8ef3495aa2b086350a23fc4c28 /corpus/support/quote-norm.pl | |
parent | 2a48d73eb794fdd736d1df035c8a31af887cde0a (diff) | |
parent | cba324bee086f4dd0fc9df204d33ff7eb9b6c323 (diff) |
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'corpus/support/quote-norm.pl')
-rwxr-xr-x | corpus/support/quote-norm.pl | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/corpus/support/quote-norm.pl b/corpus/support/quote-norm.pl index e4e5055e..b104e73c 100755 --- a/corpus/support/quote-norm.pl +++ b/corpus/support/quote-norm.pl @@ -11,6 +11,8 @@ while(<STDIN>) { s/&\s*squot\s*;/'/gi; s/&\s*quot\s*;/"/gi; s/&\s*amp\s*;/&/gi; + s/&\s*nbsp\s*;/&/gi; + s/&\s*#\s*160\s*;/ /gi; s/ (\d\d): (\d\d)/ $1:$2/g; s/[\x{20a0}]\x{20ac}]/ EUR /g; s/[\x{00A3}]/ GBP /g; @@ -20,6 +22,7 @@ while(<STDIN>) { s/&\s*#45\s*;/--/g; s/�c/--/g; s/ ,,/ "/g; + s/„/"/g; s/``/"/g; s/''/"/g; s/[「」]/"/g; |