Skip to content

keep CHARBOUND grapheme breaks around decomposed Hangul syllables #377

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shamsManna wants to merge 1 commit into
base: master
Choose a base branch
from
Open

keep CHARBOUND grapheme breaks around decomposed Hangul syllables #377

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 19 additions & 0 deletions test/misc.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,12 +87,31 @@ static void issue288(void) /* #288 */
printf("PASSED: utf8proc_normalize_utf32 preserves uninterpretable codepoints\n");
}

/* UTF8PROC_CHARBOUND must still mark grapheme breaks around Hangul
syllables that are decomposed by UTF8PROC_COMPOSE or UTF8PROC_DECOMPOSE */
static void hangul_charbound(void)
{
utf8proc_uint8_t input[] = {0x0d, 0xea, 0xb0, 0x80, 0xea, 0xb0, 0x81, 0x0a, 0x00}; /* "\r가각\n" */
utf8proc_uint8_t charbound[] = {0xff, 0x0d, 0xff, 0xea, 0xb0, 0x80, 0xff, 0xea, 0xb0, 0x81, 0xff, 0x0a, 0x00};
utf8proc_uint8_t nfd[] = {0xff, 0x0d, 0xff, 0xe1, 0x84, 0x80, 0xe1, 0x85, 0xa1,
0xff, 0xe1, 0x84, 0x80, 0xe1, 0x85, 0xa1, 0xe1, 0x86, 0xa8, 0xff, 0x0a, 0x00};
utf8proc_uint8_t *output;

utf8proc_map(input, 0, &output, UTF8PROC_NULLTERM | UTF8PROC_CHARBOUND);
check_compare("CHARBOUND", input, charbound, output, 1);
utf8proc_map(input, 0, &output, UTF8PROC_NULLTERM | UTF8PROC_STABLE | UTF8PROC_COMPOSE | UTF8PROC_CHARBOUND);
check_compare("NFC+CHARBOUND", input, charbound, output, 1);
utf8proc_map(input, 0, &output, UTF8PROC_NULLTERM | UTF8PROC_STABLE | UTF8PROC_DECOMPOSE | UTF8PROC_CHARBOUND);
check_compare("NFD+CHARBOUND", input, nfd, output, 1);
}

int main(void)
{
issue128();
issue102();
issue317();
issue288();
hangul_charbound();
#ifdef UNICODE_VERSION
printf("Unicode version: Makefile has %s, has API %s\n", UNICODE_VERSION, utf8proc_unicode_version());
check(!strcmp(UNICODE_VERSION, utf8proc_unicode_version()), "utf8proc_unicode_version mismatch");
Expand Down
10 changes: 10 additions & 0 deletions utf8proc.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -453,6 +453,16 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc,
if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT) {
utf8proc_int32_t hangul_tindex;
/* the jamo never break among themselves (GB6-GB8), and the syllable's
LV/LVT boundclass breaks and updates the state just like they do */
if ((options & UTF8PROC_CHARBOUND) &&
grapheme_break_extended(0, property->boundclass, 0, property->indic_conjunct_break,
last_boundclass)) {
if (bufsize >= 1) dst[0] = -1; /* sentinel value for grapheme break */
return 1 + utf8proc_decompose_char(uc, (bufsize >= 1) ? dst+1 : dst,
(bufsize >= 1) ? bufsize-1 : 0, options & ~(unsigned int)UTF8PROC_CHARBOUND,
last_boundclass);
}
if (bufsize >= 1) {
dst[0] = UTF8PROC_HANGUL_LBASE +
hangul_sindex / UTF8PROC_HANGUL_NCOUNT;
Expand Down
Loading