Timerix/utf8proc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

uppercase mapping ß (U+00df) to ẞ (U+1E9E) (#134)

Browse Source 
* uppercase(0x00df) = 0x1e9e

* tests for titlecase and u+00df uppercase

* NEWS, another test
This commit is contained in:
Steven G. Johnson
2018-05-02 14:18:26 -04:00
committed by GitHub
parent 8639450134
commit d81308faba
5 changed files with 1312 additions and 1276 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
test/case.c
View File

@@ -13,13 +13,20 @@ int main(int argc, char **argv)
for (c = 0; c <= 0x110000; ++c) {
utf8proc_int32_t l = utf8proc_tolower(c);
utf8proc_int32_t u = utf8proc_toupper(c);
utf8proc_int32_t t = utf8proc_totitle(c);
check(l == c || utf8proc_codepoint_valid(l), "invalid tolower");
check(u == c || utf8proc_codepoint_valid(u), "invalid toupper");
check(t == c || utf8proc_codepoint_valid(t), "invalid totitle");
if (utf8proc_codepoint_valid(c) && (l == u) != (l == t)) {
fprintf(stderr, "unexpected titlecase %x for lowercase %x / uppercase %x\n", t, l, c);
++error;
}
if (sizeof(wint_t) > 2 || c < (1<<16)) {
wint_t l0 = towlower(c), u0 = towupper(c);
/* OS unicode tables may be out of date. But if they
do have a lower/uppercase mapping, hopefully it
is correct? */
@@ -44,6 +51,20 @@ int main(int argc, char **argv)
}
}
check(!error, "utf8proc case conversion FAILED %d tests.", error);
/* issue #130 */
check(utf8proc_toupper(0x00df) == 0x1e9e &&
utf8proc_totitle(0x00df) == 0x1e9e &&
utf8proc_tolower(0x00df) == 0x00df &&
utf8proc_tolower(0x1e9e) == 0x00df &&
utf8proc_toupper(0x1e9e) == 0x1e9e,
"incorrect 0x00df/0x1e9e case conversions");
utf8proc_uint8_t str_00df[] = {0xc3, 0x9f, 0x00};
utf8proc_uint8_t str_1e9e[] = {0xe1, 0xba, 0x9e, 0x00};
check(!strcmp((char*)utf8proc_NFKC_Casefold(str_00df), "ss") &&
!strcmp((char*)utf8proc_NFKC_Casefold(str_1e9e), "ss"),
"incorrect 0x00df/0x1e9e casefold normalization");
printf("More up-to-date than OS unicode tables for %d tests.\n", better);
printf("utf8proc case conversion tests SUCCEEDED.\n");
return 0;

93
test/printproperty.c
View File

@@ -4,46 +4,57 @@
int main(int argc, char **argv)
{
int i;
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;
for (i = 1; i < argc; ++i) {
utf8proc_uint8_t cstr[16], *map;
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);
if (utf8proc_codepoint_valid(c))
cstr[utf8proc_encode_char(c, cstr)] = 0;
else
strcat((char*)cstr, "N/A");
utf8proc_map(cstr, 0, &map, UTF8PROC_NULLTERM | UTF8PROC_CASEFOLD);
printf("U+%s: %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"
" casefold = %s\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], (char*) cstr,
utf8proc_category_string(c),
p->combining_class,
p->bidi_class,
p->decomp_type,
utf8proc_toupper(c),
utf8proc_tolower(c),
utf8proc_totitle(c),
(char *) map,
p->comb_index,
p->bidi_mirrored,
p->comp_exclusion,
p->ignorable,
p->control_boundary,
p->boundclass,
utf8proc_charwidth(c));
free(map);
}
return 0;
}