Differential D6198 Diff 19467 source/blender/blenlib/intern/string_utf8.c

Changeset View

Standalone View

source/blender/blenlib/intern/string_utf8.c

Show First 20 Lines • Show All 424 Lines • ▼ Show 20 Lines
#ifdef DEBUG_STRSIZE		#ifdef DEBUG_STRSIZE
memset(dst_w, 0xff, sizeof(dst_w) maxncpy);		memset(dst_w, 0xff, sizeof(dst_w) maxncpy);
#endif		#endif

while (*src_c && len != maxlen) {		while (*src_c && len != maxlen) {
size_t step = 0;		size_t step = 0;
uint unicode = BLI_str_utf8_as_unicode_and_size(src_c, &step);		uint unicode = BLI_str_utf8_as_unicode_and_size(src_c, &step);
if (unicode != BLI_UTF8_ERR) {		if (unicode != BLI_UTF8_ERR) {
		/* TODO: `wchar_t` type is an implementation-defined and may represent
		* 16-bit or 32-bit depending on operating system.
		* So the ideal would be to do the corresponding encoding.
		* But for now just assert that it has no conflicting use. */
		BLI_assert(step <= sizeof(wchar_t));
*dst_w = (wchar_t)unicode;		*dst_w = (wchar_t)unicode;
src_c += step;		src_c += step;
}		}
else {		else {
*dst_w = '?';		*dst_w = '?';
src_c = BLI_str_find_next_char_utf8(src_c, NULL);		src_c = BLI_str_find_next_char_utf8(src_c, NULL);
}		}
dst_w++;		dst_w++;
len++;		len++;
}		}

*dst_w = 0;		*dst_w = 0;

return len;		return len;
}		}

/* end wchar_t / utf8 functions */		/* end wchar_t / utf8 functions */
/* --------------------------------------------------------------------------*/		/* --------------------------------------------------------------------------*/

/* count columns that character/string occupies, based on wcwidth.c */		/* count columns that character/string occupies, based on wcwidth.c */

int BLI_wcwidth(wchar_t ucs)		int BLI_wcwidth(char32_t ucs)
{		{
return mk_wcwidth(ucs);		return mk_wcwidth(ucs);
}		}

int BLI_wcswidth(const wchar_t *pwcs, size_t n)		int BLI_wcswidth(const char32_t *pwcs, size_t n)
{		{
return mk_wcswidth(pwcs, n);		return mk_wcswidth(pwcs, n);
}		}

int BLI_str_utf8_char_width(const char *p)		int BLI_str_utf8_char_width(const char *p)
{		{
uint unicode = BLI_str_utf8_as_unicode(p);		uint unicode = BLI_str_utf8_as_unicode(p);
if (unicode == BLI_UTF8_ERR) {		if (unicode == BLI_UTF8_ERR) {
return -1;		return -1;
}		}

return BLI_wcwidth((wchar_t)unicode);		return BLI_wcwidth((char32_t)unicode);
}		}

int BLI_str_utf8_char_width_safe(const char *p)		int BLI_str_utf8_char_width_safe(const char *p)
{		{
int columns;		int columns;

uint unicode = BLI_str_utf8_as_unicode(p);		uint unicode = BLI_str_utf8_as_unicode(p);
if (unicode == BLI_UTF8_ERR) {		if (unicode == BLI_UTF8_ERR) {
return 1;		return 1;
}		}

columns = BLI_wcwidth((wchar_t)unicode);		columns = BLI_wcwidth((char32_t)unicode);

return (columns < 0) ? 1 : columns;		return (columns < 0) ? 1 : columns;
}		}

/* --------------------------------------------------------------------------*/		/* --------------------------------------------------------------------------*/

/* copied from glib's gutf8.c, added 'Err' arg */		/* copied from glib's gutf8.c, added 'Err' arg */

▲ Show 20 Lines • Show All 229 Lines • ▼ Show 20 Lines	for (i = len - 1; i > 0; i--) {
c >>= 6;		c >>= 6;
}		}
outbuf[0] = c \| first;		outbuf[0] = c \| first;
}		}

return len;		return len;
}		}

		size_t BLI_str_utf8_as_utf32(char32_t *__restrict dst_w,
		const char *__restrict src_c,
		const size_t maxncpy)
		{
		const size_t maxlen = maxncpy - 1;
		size_t len = 0;

		BLI_assert(maxncpy != 0);

		#ifdef DEBUG_STRSIZE
		memset(dst_w, 0xff, sizeof(dst_w) maxncpy);
		#endif

		while (*src_c && len != maxlen) {
		size_t step = 0;
		uint unicode = BLI_str_utf8_as_unicode_and_size(src_c, &step);
		if (unicode != BLI_UTF8_ERR) {
		*dst_w = unicode;
		src_c += step;
		}
		else {
		*dst_w = '?';
		src_c = BLI_str_find_next_char_utf8(src_c, NULL);
		}
		dst_w++;
		len++;
		}

		*dst_w = 0;

		return len;
		}

		size_t BLI_str_utf32_as_utf8(char *__restrict dst,
		const char32_t *__restrict src,
		const size_t maxncpy)
		{
		const size_t maxlen = maxncpy - 1;
		/* 6 is max utf8 length of an unicode char. */
		const int64_t maxlen_secured = (int64_t)maxlen - 6;
		size_t len = 0;

		BLI_assert(maxncpy != 0);

		#ifdef DEBUG_STRSIZE
		memset(dst, 0xff, sizeof(dst) maxncpy);
		#endif

		while (*src && len <= maxlen_secured) {
		len += BLI_str_utf8_from_unicode((uint)*src++, dst + len);
		}

		/* We have to be more careful for the last six bytes,
		* to avoid buffer overflow in case utf8-encoded char would be too long for our dst buffer. */
		while (*src) {
		char t[6];
		size_t l = BLI_str_utf8_from_unicode((uint)*src++, t);
		BLI_assert(l <= 6);
		if (len + l > maxlen) {
		break;
		}
		memcpy(dst + len, t, l);
		len += l;
		}

		dst[len] = '\0';

		return len;
		}

		/* utf32 len in utf8 */
		size_t BLI_str_utf32_as_utf8_len(const char32_t *src)
		{
		size_t len = 0;

		while (*src) {
		len += BLI_str_utf8_from_unicode((uint)*src++, NULL);
		}

		return len;
		}

/* was g_utf8_find_prev_char */		/* was g_utf8_find_prev_char */
/**		/**
* BLI_str_find_prev_char_utf8:		* BLI_str_find_prev_char_utf8:
* \param str: pointer to the beginning of a UTF-8 encoded string		* \param str: pointer to the beginning of a UTF-8 encoded string
* \param p: pointer to some position within \a str		* \param p: pointer to some position within \a str
*		*
* Given a position \a p with a UTF-8 encoded string \a str, find the start		* Given a position \a p with a UTF-8 encoded string \a str, find the start
* of the previous UTF-8 character starting before. \a p Returns %NULL if no		* of the previous UTF-8 character starting before. \a p Returns %NULL if no
▲ Show 20 Lines • Show All 184 Lines • Show Last 20 Lines