eeebf70bcf
* 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
50 lines
1.6 KiB
C
50 lines
1.6 KiB
C
/* simple test program to print out the utf8proc properties for a codepoint */
|
|
|
|
#include "tests.h"
|
|
|
|
int main(int argc, char **argv)
|
|
{
|
|
int i;
|
|
|
|
for (i = 1; i < argc; ++i) {
|
|
unsigned int c;
|
|
if (!strcmp(argv[i], "-V")) {
|
|
printf("utf8proc version %s\n", utf8proc_version());
|
|
continue;
|
|
}
|
|
check(sscanf(argv[i],"%x",&c) == 1, "invalid hex input %s", argv[i]);
|
|
const utf8proc_property_t *p = utf8proc_get_property(c);
|
|
printf("U+%s:\n"
|
|
" category = %s\n"
|
|
" combining_class = %d\n"
|
|
" bidi_class = %d\n"
|
|
" decomp_type = %d\n"
|
|
" uppercase_mapping = %x\n"
|
|
" lowercase_mapping = %x\n"
|
|
" titlecase_mapping = %x\n"
|
|
" comb_index = %d\n"
|
|
" bidi_mirrored = %d\n"
|
|
" comp_exclusion = %d\n"
|
|
" ignorable = %d\n"
|
|
" control_boundary = %d\n"
|
|
" boundclass = %d\n"
|
|
" charwidth = %d\n",
|
|
argv[i],
|
|
utf8proc_category_string(c),
|
|
p->combining_class,
|
|
p->bidi_class,
|
|
p->decomp_type,
|
|
utf8proc_toupper(c),
|
|
utf8proc_tolower(c),
|
|
utf8proc_totitle(c),
|
|
p->comb_index,
|
|
p->bidi_mirrored,
|
|
p->comp_exclusion,
|
|
p->ignorable,
|
|
p->control_boundary,
|
|
p->boundclass,
|
|
utf8proc_charwidth(c));
|
|
}
|
|
return 0;
|
|
}
|