do not unaccent Bengali characters (process like the Hindi ones)

This commit is contained in:
Jean-Francois Dockes 2014-07-16 12:48:55 +02:00
parent 6ec7f92938
commit 91dc09bc3c
5 changed files with 1604 additions and 1698 deletions

File diff suppressed because it is too large Load diff

View file

@ -35,7 +35,7 @@ extern "C" {
#define UNAC_BLOCK_SHIFT 3
#define UNAC_BLOCK_MASK ((1 << UNAC_BLOCK_SHIFT) - 1)
#define UNAC_BLOCK_SIZE (1 << UNAC_BLOCK_SHIFT)
#define UNAC_BLOCK_COUNT 714
#define UNAC_BLOCK_COUNT 713
#define UNAC_INDEXES_SIZE (0x10000 >> UNAC_BLOCK_SHIFT)
/* Generated by builder. Do not modify. End defines */
@ -893,7 +893,6 @@ extern unsigned short unac_data709[];
extern unsigned short unac_data710[];
extern unsigned short unac_data711[];
extern unsigned short unac_data712[];
extern unsigned short unac_data713[];
/* Generated by builder. Do not modify. End declarations */
#ifdef __cplusplus

View file

@ -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*(.+)/) {

File diff suppressed because it is too large Load diff

View file

@ -35,7 +35,7 @@ extern "C" {
#define UNAC_BLOCK_SHIFT 3
#define UNAC_BLOCK_MASK ((1 << UNAC_BLOCK_SHIFT) - 1)
#define UNAC_BLOCK_SIZE (1 << UNAC_BLOCK_SHIFT)
#define UNAC_BLOCK_COUNT 714
#define UNAC_BLOCK_COUNT 713
#define UNAC_INDEXES_SIZE (0x10000 >> UNAC_BLOCK_SHIFT)
/* Generated by builder. Do not modify. End defines */
@ -893,7 +893,6 @@ extern unsigned short unac_data709[];
extern unsigned short unac_data710[];
extern unsigned short unac_data711[];
extern unsigned short unac_data712[];
extern unsigned short unac_data713[];
/* Generated by builder. Do not modify. End declarations */
#ifdef __cplusplus