do not unaccent Bengali characters (process like the Hindi ones)
This commit is contained in:
parent
6ec7f92938
commit
91dc09bc3c
5 changed files with 1604 additions and 1698 deletions
|
@ -97,6 +97,8 @@ sub main {
|
|||
# Hindi Devanagari
|
||||
&& !(hex $code_value >= 0x0900 && hex $code_value <= 0x097f)
|
||||
&& !(hex $code_value >= 0xa8e0 && hex $code_value <= 0xa8ff)
|
||||
# Bengali
|
||||
&& !(hex $code_value >= 0x0980 && hex $code_value <= 0x09ff)
|
||||
) {
|
||||
# If a decomposition exists, record it
|
||||
if($character_decomposition_mapping =~ /(<.*>)?\s*(.+)/) {
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue