Add Unicode support to String.to_*_case() methods

This commit is contained in:
Danil Alexeev 2024-02-22 12:18:45 +03:00
parent 16d61427ca
commit c0aa88ae4f
No known key found for this signature in database
GPG key ID: 124453E157DA8DC7
4 changed files with 1387 additions and 45 deletions

File diff suppressed because it is too large Load diff

View file

@ -35,24 +35,43 @@
#include "char_range.inc"
#define BSEARCH_CHAR_RANGE(m_array) \
int low = 0; \
int high = sizeof(m_array) / sizeof(m_array[0]) - 1; \
int middle; \
\
while (low <= high) { \
middle = (low + high) / 2; \
\
if (c < m_array[middle].start) { \
high = middle - 1; \
} else if (c > m_array[middle].end) { \
low = middle + 1; \
} else { \
return true; \
} \
} \
\
return false
static _FORCE_INLINE_ bool is_unicode_identifier_start(char32_t c) {
for (int i = 0; xid_start[i].start != 0; i++) {
if (c >= xid_start[i].start && c <= xid_start[i].end) {
return true;
}
}
return false;
BSEARCH_CHAR_RANGE(xid_start);
}
static _FORCE_INLINE_ bool is_unicode_identifier_continue(char32_t c) {
for (int i = 0; xid_continue[i].start != 0; i++) {
if (c >= xid_continue[i].start && c <= xid_continue[i].end) {
return true;
}
}
return false;
BSEARCH_CHAR_RANGE(xid_continue);
}
static _FORCE_INLINE_ bool is_unicode_upper_case(char32_t c) {
BSEARCH_CHAR_RANGE(uppercase_letter);
}
static _FORCE_INLINE_ bool is_unicode_lower_case(char32_t c) {
BSEARCH_CHAR_RANGE(lowercase_letter);
}
#undef BSEARCH_CHAR_RANGE
static _FORCE_INLINE_ bool is_ascii_upper_case(char32_t c) {
return (c >= 'A' && c <= 'Z');
}

View file

@ -1044,17 +1044,17 @@ String String::_camelcase_to_underscore() const {
int start_index = 0;
for (int i = 1; i < size(); i++) {
bool is_prev_upper = is_ascii_upper_case(cstr[i - 1]);
bool is_prev_lower = is_ascii_lower_case(cstr[i - 1]);
bool is_prev_upper = is_unicode_upper_case(cstr[i - 1]);
bool is_prev_lower = is_unicode_lower_case(cstr[i - 1]);
bool is_prev_digit = is_digit(cstr[i - 1]);
bool is_curr_upper = is_ascii_upper_case(cstr[i]);
bool is_curr_lower = is_ascii_lower_case(cstr[i]);
bool is_curr_upper = is_unicode_upper_case(cstr[i]);
bool is_curr_lower = is_unicode_lower_case(cstr[i]);
bool is_curr_digit = is_digit(cstr[i]);
bool is_next_lower = false;
if (i + 1 < size()) {
is_next_lower = is_ascii_lower_case(cstr[i + 1]);
is_next_lower = is_unicode_lower_case(cstr[i + 1]);
}
const bool cond_a = is_prev_lower && is_curr_upper; // aA