Stephen Dolan
ff48bd6ec5
In particular, parse bad UTF8 by replacing the broken bits with U+FFFD and resychronise correctly after broken sequences.
12 lines
318 B
C
12 lines
318 B
C
#ifndef JV_UNICODE_H
|
|
#define JV_UNICODE_H
|
|
|
|
const char* jvp_utf8_next(const char* in, const char* end, int* codepoint);
|
|
int jvp_utf8_is_valid(const char* in, const char* end);
|
|
|
|
int jvp_utf8_decode_length(char startchar);
|
|
|
|
int jvp_utf8_encode_length(int codepoint);
|
|
int jvp_utf8_encode(int codepoint, char* out);
|
|
#endif
|