utf8: add utf8_n_codepoints() for counting complete utf8 codepoints in a string

This commit is contained in:
Lennart Poettering 2018-02-14 18:41:03 +01:00
parent 7b91264852
commit 65ee8660df
2 changed files with 21 additions and 0 deletions

View file

@ -408,3 +408,22 @@ int utf8_encoded_valid_unichar(const char *str) {
return len;
}
size_t utf8_n_codepoints(const char *str) {
size_t n = 0;
/* Returns the number of UTF-8 codepoints in this string, or (size_t) -1 if the string is not valid UTF-8. */
while (*str != 0) {
int k;
k = utf8_encoded_valid_unichar(str);
if (k < 0)
return (size_t) -1;
str += k;
n++;
}
return n;
}

View file

@ -59,3 +59,5 @@ static inline bool utf16_is_trailing_surrogate(char16_t c) {
static inline char32_t utf16_surrogate_pair_to_unichar(char16_t lead, char16_t trail) {
return ((lead - 0xd800) << 10) + (trail - 0xdc00) + 0x10000;
}
size_t utf8_n_codepoints(const char *str);