Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/moses-smt/mosesdecoder.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rwxr-xr-xscripts/ems/support/split-sentences.perl2
1 files changed, 1 insertions, 1 deletions
diff --git a/scripts/ems/support/split-sentences.perl b/scripts/ems/support/split-sentences.perl
index a1cfb0d37..d4e0161bf 100755
--- a/scripts/ems/support/split-sentences.perl
+++ b/scripts/ems/support/split-sentences.perl
@@ -191,7 +191,7 @@ sub preprocess {
my $starting_punct = $2;
if ($prefix && $NONBREAKING_PREFIX{$prefix} && $NONBREAKING_PREFIX{$prefix} == 1 && !$starting_punct) {
# Not breaking;
- } elsif ($words[$i] =~ /(\.)[\p{IsUpper}\-]+(\.+)$/) {
+ } elsif ($words[$i] =~ /(\.?)[\p{IsUpper}\-]+(\.+)$/) {
# Not breaking - upper case acronym
} elsif($words[$i+1] =~ /^([ ]*[\'\"\(\[\¿\¡\p{IsPi}]*[ ]*[\p{IsUpper}0-9])/) {
# The next word has a bunch of initial quotes, maybe a