summaryrefslogtreecommitdiff
path: root/corpus/support/tokenizer.pl
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2014-10-13 19:03:48 +0100
committerPatrick Simianer <p@simianer.de>2014-10-13 19:03:48 +0100
commitcb9fb7088dde35881516c088db402abe747d49fa (patch)
treea91e4935a7941f1b261f76d88ab41fa3078a1891 /corpus/support/tokenizer.pl
parent0a00e57e921c8eca8e02364db7d2e6607bfdcebc (diff)
parentb1ed81ef3216b212295afa76c5d20a56fb647204 (diff)
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'corpus/support/tokenizer.pl')
-rwxr-xr-xcorpus/support/tokenizer.pl2
1 files changed, 1 insertions, 1 deletions
diff --git a/corpus/support/tokenizer.pl b/corpus/support/tokenizer.pl
index f57bc87a..aa285be4 100755
--- a/corpus/support/tokenizer.pl
+++ b/corpus/support/tokenizer.pl
@@ -386,7 +386,7 @@ sub deep_proc_token {
}
##### step 1: separate by punct T2 on the boundary
- my $t2 = '\`|\!|\@|\+|\=|\[|\]|\<|\>|\||\(|\)|\{|\}|\?|\"|;';
+ my $t2 = '\`|\!|\@|\+|\=|\[|\]|\<|\>|\||\(|\)|\{|\}|\?|\"|;|●|○';
if($line =~ s/^(($t2)+)/$1 /){
return proc_line($line);
}