diff options
| author | Barry Haddow <barry.haddow@gmail.com> | 2019-09-30 18:53:06 +0300 |
|---|---|---|
| committer | Barry Haddow <barry.haddow@gmail.com> | 2019-09-30 18:53:06 +0300 |
| commit | 9bffde57ba1a6e03a101b8826220609bbb49743a (patch) | |
| tree | e3195f82c1c9f2e5b62d34ea5452462dfa26ff73 /scripts/ems/support | |
| parent | 257d7e5e663a6bba97a21b191a04a9684f5e8436 (diff) | |
revert 05788925
Diffstat (limited to 'scripts/ems/support')
| -rwxr-xr-x | scripts/ems/support/split-sentences.perl | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/scripts/ems/support/split-sentences.perl b/scripts/ems/support/split-sentences.perl index 8062e2942..49d599430 100755 --- a/scripts/ems/support/split-sentences.perl +++ b/scripts/ems/support/split-sentences.perl @@ -202,7 +202,7 @@ 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 |