diff options
Diffstat (limited to 'corpus')
| -rwxr-xr-x | corpus/support/quote-norm.pl | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/corpus/support/quote-norm.pl b/corpus/support/quote-norm.pl index 57f4ad77..7fe33db4 100755 --- a/corpus/support/quote-norm.pl +++ b/corpus/support/quote-norm.pl @@ -61,6 +61,11 @@ while(<STDIN>) { s/«/"/g; s/»/"/g; tr/！-～/!-~/; + tr/०-९/0-9/; # devangari + tr/౦-౯/0-9/; # telugu + tr/೦-೯/0-9/; # kannada + tr/೦-௯/0-9/; # tamil + tr/൦-൯/0-9/; # malayalam s/、/,/g; # s/。/./g; s/…/.../g; |