diff options
| author | Barry Haddow <barry.haddow@gmail.com> | 2019-10-31 19:12:59 +0300 |
|---|---|---|
| committer | Barry Haddow <barry.haddow@gmail.com> | 2019-10-31 19:12:59 +0300 |
| commit | d708e26b60ea8496fd41ed7fd512eb67bd9015ac (patch) | |
| tree | 635869b2f782419b4618a11aea1553c2dd0a47d8 /scripts/ems/support | |
| parent | 0fef8ebf4cd8fd4ffb3cca69b003ae7bae3a91b5 (diff) | |
use block notation for indic scripts
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 6268e1d68..e553c3b05 100755 --- a/scripts/ems/support/split-sentences.perl +++ b/scripts/ems/support/split-sentences.perl @@ -170,7 +170,7 @@ sub preprocess { ) \s+ ( [\'\"\x{201e}\x{bb}\(\[\¿\¡\p{IsPi}]* - [\x{0900}-\x{097F}\x{0a80}-\x{0aff}] + [\p{Block: Devanagari_Extended}\p{Block: Gujarati}] ) }{$1\n$2}gx; } |