[utils] adding string_is_digit function, similar to Python\'s (i.e. counts if it's in the Nd unicode category)
This commit is contained in:
@@ -482,6 +482,32 @@ inline size_t utf8_common_prefix_ignore_separators(const char *str1, const char
|
||||
return utf8_common_prefix_len_ignore_separators(str1, str2, strlen(str2));
|
||||
}
|
||||
|
||||
bool string_is_digit(char *str, size_t len) {
|
||||
uint8_t *ptr = (uint8_t *)str;
|
||||
size_t idx = 0;
|
||||
|
||||
bool ignorable = true;
|
||||
|
||||
while (idx < len) {
|
||||
int32_t ch;
|
||||
ssize_t char_len = utf8proc_iterate(ptr, len, &ch);
|
||||
|
||||
if (char_len <= 0) break;
|
||||
if (ch == 0) break;
|
||||
if (!(utf8proc_codepoint_valid(ch))) return false;
|
||||
|
||||
int cat = utf8proc_category(ch);
|
||||
if (cat != UTF8PROC_CATEGORY_ND) {
|
||||
return false;
|
||||
}
|
||||
|
||||
ptr += char_len;
|
||||
idx += char_len;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
bool string_is_ignorable(char *str, size_t len) {
|
||||
uint8_t *ptr = (uint8_t *)str;
|
||||
size_t idx = 0;
|
||||
|
||||
@@ -92,6 +92,7 @@ bool utf8_is_symbol(int cat);
|
||||
bool utf8_is_separator(int cat);
|
||||
bool utf8_is_whitespace(int32_t ch);
|
||||
|
||||
bool string_is_digit(char *str, size_t len);
|
||||
bool string_is_ignorable(char *str, size_t len);
|
||||
|
||||
ssize_t string_next_hyphen_index(char *str, size_t len);
|
||||
|
||||
Reference in New Issue
Block a user