Smaller tables (#68)
* convert sequences to utf-16 (saves 25kb) * store sequence length in properties instead using -1 termination (saves 10kb) * cache index for slightly faster data creation * store lower/upper/title mapping in sequence array (saves 25kb). Add utf8proc_totitle, as title_mapping cannot be used to get the title codepoint anymore. Rename xxx_mapping to xxx_seqindex, so programs assuming a value with the old meaning fail at compile time * change combination array data type to uint16 (saves 40kb) * merge 1st and 2nd comb index (saves 50kb) * kill empty prefix/suffix in combination array (saves 50kb) * there was no need to have a separate combination start array, it can be merged in a single array * some fixes * mark the table as const again * and regen
This commit is contained in:
committed by
Steven G. Johnson
parent
9a0b87b57e
commit
eeebf70bcf
@@ -22,8 +22,7 @@ int main(int argc, char **argv)
|
||||
" uppercase_mapping = %x\n"
|
||||
" lowercase_mapping = %x\n"
|
||||
" titlecase_mapping = %x\n"
|
||||
" comb1st_index = %d\n"
|
||||
" comb2nd_index = %d\n"
|
||||
" comb_index = %d\n"
|
||||
" bidi_mirrored = %d\n"
|
||||
" comp_exclusion = %d\n"
|
||||
" ignorable = %d\n"
|
||||
@@ -35,11 +34,10 @@ int main(int argc, char **argv)
|
||||
p->combining_class,
|
||||
p->bidi_class,
|
||||
p->decomp_type,
|
||||
p->uppercase_mapping,
|
||||
p->lowercase_mapping,
|
||||
p->titlecase_mapping,
|
||||
p->comb1st_index,
|
||||
p->comb2nd_index,
|
||||
utf8proc_toupper(c),
|
||||
utf8proc_tolower(c),
|
||||
utf8proc_totitle(c),
|
||||
p->comb_index,
|
||||
p->bidi_mirrored,
|
||||
p->comp_exclusion,
|
||||
p->ignorable,
|
||||
|
||||
Reference in New Issue
Block a user