Differential D6198 Diff 19450 source/blender/blenlib/intern/string_utf8.c

Changeset View

Standalone View

source/blender/blenlib/intern/string_utf8.c

Show First 20 Lines • Show All 483 Lines • ▼ Show 20 Lines	int BLI_str_utf8_char_width_safe(const char *p)

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 */

/* note, glib uses uint for unicode, best we do the same,		/* note, glib uses uint for unicode, best we do the same - campbell */
* though we don't typedef it - campbell */

#define UTF8_COMPUTE(Char, Mask, Len, Err) \		#define UTF8_COMPUTE(Char, Mask, Len, Err) \
if (Char < 128) { \		if (Char < 128) { \
Len = 1; \		Len = 1; \
Mask = 0x7f; \		Mask = 0x7f; \
} \		} \
else if ((Char & 0xe0) == 0xc0) { \		else if ((Char & 0xe0) == 0xc0) { \
Len = 2; \		Len = 2; \
▲ Show 20 Lines • Show All 219 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;
		}

		/* len of utf8 in unicode array */
		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