diff options
| author | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2013-03-03 12:06:43 +0100 |
|---|---|---|
| committer | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2013-03-03 12:06:43 +0100 |
| commit | f7f9048f8e4d34682f17bfd050d238005feb3ee3 (patch) | |
| tree | fa20fa16b0f5a8009a9254622b65ebeaec049399 /corpus/support/tokenizer.pl | |
| parent | 9d306b30c9abba995ba35243e5cb461bb472a61f (diff) | |
| parent | 12f2eab0e7dc7167af47cddf8ef88968656277da (diff) | |
Merge branch 'master' of github.com:pks/cdec-dtrain
Diffstat (limited to 'corpus/support/tokenizer.pl')
| -rwxr-xr-x | corpus/support/tokenizer.pl | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/corpus/support/tokenizer.pl b/corpus/support/tokenizer.pl index e9c3a37d..0350a894 100755 --- a/corpus/support/tokenizer.pl +++ b/corpus/support/tokenizer.pl @@ -73,6 +73,7 @@ my $dict_file = "$workdir/token_list"; my $word_patt_file = "$workdir/token_patterns"; open(my $dict_fp, "$dict_file") or die; +binmode($dict_fp, ":utf8"); # read in the list of words that should not be segmented, ## e.g.,"I.B.M.", co-operation. @@ -89,6 +90,7 @@ while(<$dict_fp>){ } open(my $patt_fp, "$word_patt_file") or die; +binmode($patt_fp, ":utf8"); my @word_patts = (); my $word_patt_num = 0; while(<$patt_fp>){ @@ -147,7 +149,6 @@ while(<STDIN>){ print STDOUT " $new_line\n"; } -print STDERR "\n"; ######################################################################## |