/**
* g_utf8_get_char:
* @p: a pointer to Unicode character encoded as UTF-8
*
* Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
*
* If @p does not point to a valid UTF-8 encoded character, results
* are undefined. If you are not sure that the bytes are complete
* valid Unicode characters, you should use g_utf8_get_char_validated()
* instead.
*
* Return value: the resulting character
*/
gunichar
g_utf8_get_char (const gchar *p)
{
int i, mask = 0, len;
gunichar result;
unsigned char c = (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1)
return (gunichar)-1;
UTF8_GET (result, p, i, mask, len);
return result;
}
/*
* g_utf8_get_char:
* @p: a pointer to Unicode character encoded as UTF-8
*
* Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
* If @p does not point to a valid UTF-8 encoded character, results are
* undefined. If you are not sure that the bytes are complete
* valid Unicode characters, you should use g_utf8_get_char_validated()
* instead.
*
* Return value: the resulting character
**/
static unsigned int
cc_utf8_get_char (const char * p)
{
int i, mask = 0, len;
unsigned int result;
unsigned char c = (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1)
return (unsigned int) - 1;
UTF8_GET (result, p, i, mask, len);
return result;
}
/* another variant that steps over the index,
* note, currently this also falls back to latin1 for text drawing. */
unsigned int BLI_str_utf8_as_unicode_step(const char *p, size_t *index)
{
int i, mask = 0, len;
unsigned int result;
unsigned char c;
p += *index;
c= (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1) {
/* when called with NULL end, result will never be NULL,
* checks for a NULL character */
char *p_next= BLI_str_find_next_char_utf8(p, NULL);
/* will never return the same pointer unless '\0',
* eternal loop is prevented */
*index += (size_t)(p_next - p);
return BLI_UTF8_ERR;
}
/* this is tricky since there are a few ways we can bail out of bad unicode
* values, 3 possible solutions. */
#if 0
UTF8_GET (result, p, i, mask, len, BLI_UTF8_ERR);
#elif 1
/* WARNING: this is NOT part of glib, or supported by similar functions.
* this is added for text drawing because some filepaths can have latin1
* characters */
UTF8_GET (result, p, i, mask, len, BLI_UTF8_ERR);
if (result == BLI_UTF8_ERR) {
len= 1;
result= *p;
}
/* end warning! */
#else
/* without a fallback like '?', text drawing will stop on this value */
UTF8_GET (result, p, i, mask, len, '?');
#endif
*index += len;
return result;
}
/**
* _cairo_utf8_get_char_validated:
* @p: a UTF-8 string
* @unicode: location to store one Unicode character
*
* Decodes the first character of a valid UTF-8 string, and returns
* the number of bytes consumed.
*
* Note that the string should be valid. Do not use this without
* validating the string first.
*
* Returns: the number of bytes forming the character returned.
**/
int
_cairo_utf8_get_char_validated (const char *p,
uint32_t *unicode)
{
int i, mask = 0, len;
uint32_t result;
unsigned char c = (unsigned char) *p;
UTF8_COMPUTE (c, mask, len);
if (len == -1) {
if (unicode)
*unicode = (uint32_t)-1;
return 1;
}
UTF8_GET (result, p, i, mask, len);
if (unicode)
*unicode = result;
return len;
}
