Page MenuHome
Differential D4455 Diff 14273 source/blender/blenlib/intern/string_utf8.c

Changeset View

Standalone View

View Options

source/blender/blenlib/intern/string_utf8.c

Show First 20 Lines • Show All 513 Lines • ▼ Show 20 Lines
* *
* Converts a sequence of bytes encoded as UTF-8 to a Unicode character. * Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
* If \a p does not point to a valid UTF-8 encoded character, results are * If \a p does not point to a valid UTF-8 encoded character, results are
* undefined. If you are not sure that the bytes are complete * undefined. If you are not sure that the bytes are complete
* valid Unicode characters, you should use g_utf8_get_char_validated() * valid Unicode characters, you should use g_utf8_get_char_validated()
* instead. * instead.
* *
* Return value: the resulting character * Return value: the resulting character
**/ */
uint BLI_str_utf8_as_unicode(const char *p) uint BLI_str_utf8_as_unicode(const char *p)
{ {
int i, len; int i, len;
uint mask = 0; uint mask = 0;
uint result; uint result;
const unsigned char c = (unsigned char) *p; const unsigned char c = (unsigned char) *p;
UTF8_COMPUTE(c, mask, len, -1); UTF8_COMPUTE(c, mask, len, -1);
▲ Show 20 Lines • Show All 89 Lines • ▼ Show 20 Lines
* \param c: a Unicode character code * \param c: a Unicode character code
* \param outbuf: output buffer, must have at least 6 bytes of space. * \param outbuf: output buffer, must have at least 6 bytes of space.
* If %NULL, the length will be computed and returned * If %NULL, the length will be computed and returned
* and nothing will be written to outbuf. * and nothing will be written to outbuf.
* *
* Converts a single character to UTF-8. * Converts a single character to UTF-8.
* *
* \return number of bytes written * \return number of bytes written
**/ */
size_t BLI_str_utf8_from_unicode(uint c, char *outbuf) size_t BLI_str_utf8_from_unicode(uint c, char *outbuf)
{ {
/* If this gets modified, also update the copy in g_string_insert_unichar() */ /* If this gets modified, also update the copy in g_string_insert_unichar() */
uint len = 0; uint len = 0;
uint first; uint first;
uint i; uint i;
if (c < 0x80) { if (c < 0x80) {
▲ Show 20 Lines • Show All 42 Lines • ▼ Show 20 Lines
* 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
* UTF-8 characters are present in \a str before \a p * UTF-8 characters are present in \a str before \a p
* *
* \a p does not have to be at the beginning of a UTF-8 character. No check * \a p does not have to be at the beginning of a UTF-8 character. No check
* is made to see if the character found is actually valid other than * is made to see if the character found is actually valid other than
* it starts with an appropriate byte. * it starts with an appropriate byte.
* *
* Return value: a pointer to the found character or %NULL. * Return value: a pointer to the found character or %NULL.
**/ */
char *BLI_str_find_prev_char_utf8(const char *str, const char *p) char *BLI_str_find_prev_char_utf8(const char *str, const char *p)
{ {
for (--p; p >= str; --p) { for (--p; p >= str; --p) {
if ((*p & 0xc0) != 0x80) { if ((*p & 0xc0) != 0x80) {
return (char *)p; return (char *)p;
} }
} }
return NULL; return NULL;
} }
/* was g_utf8_find_next_char */ /* was g_utf8_find_next_char */
/** /**
* BLI_str_find_next_char_utf8: * BLI_str_find_next_char_utf8:
* \param p: a pointer to a position within a UTF-8 encoded string * \param p: a pointer to a position within a UTF-8 encoded string
* \param end: a pointer to the byte following the end of the string, * \param end: a pointer to the byte following the end of the string,
* or %NULL to indicate that the string is nul-terminated. * or %NULL to indicate that the string is nul-terminated.
* *
* Finds the start of the next UTF-8 character in the string after \a p * Finds the start of the next UTF-8 character in the string after \a p
* *
* \a p does not have to be at the beginning of a UTF-8 character. No check * \a p does not have to be at the beginning of a UTF-8 character. No check
* is made to see if the character found is actually valid other than * is made to see if the character found is actually valid other than
* it starts with an appropriate byte. * it starts with an appropriate byte.
* *
* Return value: a pointer to the found character or %NULL * Return value: a pointer to the found character or %NULL
**/ */
char *BLI_str_find_next_char_utf8(const char *p, const char *end) char *BLI_str_find_next_char_utf8(const char *p, const char *end)
{ {
if (*p) { if (*p) {
if (end) { if (end) {
for (++p; p < end && (*p & 0xc0) == 0x80; ++p) { for (++p; p < end && (*p & 0xc0) == 0x80; ++p) {
/* do nothing */ /* do nothing */
} }
} }
Show All 14 Lines
* Finds the previous UTF-8 character in the string before \a p * Finds the previous UTF-8 character in the string before \a p
* *
* \a p does not have to be at the beginning of a UTF-8 character. No check * \a p does not have to be at the beginning of a UTF-8 character. No check
* is made to see if the character found is actually valid other than * is made to see if the character found is actually valid other than
* it starts with an appropriate byte. If \a p might be the first * it starts with an appropriate byte. If \a p might be the first
* character of the string, you must use g_utf8_find_prev_char() instead. * character of the string, you must use g_utf8_find_prev_char() instead.
* *
* Return value: a pointer to the found character. * Return value: a pointer to the found character.
**/ */
char *BLI_str_prev_char_utf8(const char *p) char *BLI_str_prev_char_utf8(const char *p)
{ {
while (1) { while (1) {
p--; p--;
if ((*p & 0xc0) != 0x80) { if ((*p & 0xc0) != 0x80) {
return (char *)p; return (char *)p;
} }
} }
▲ Show 20 Lines • Show All 51 Lines • Show Last 20 Lines