diff options
author | Vladimir Azarov <avm@intermediate-node.net> | 2024-10-01 15:47:05 +0200 |
---|---|---|
committer | Vladimir Azarov <avm@intermediate-node.net> | 2024-10-01 15:47:05 +0200 |
commit | 4abab5ad6c8465a7528ccdd5f49367da05f78bbd (patch) | |
tree | ebf009bf1376a5a223a915bc27cbbd791a1316bc /src/multibyte/mbrtoc16.c |
Initial version
Diffstat (limited to 'src/multibyte/mbrtoc16.c')
-rw-r--r-- | src/multibyte/mbrtoc16.c | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/src/multibyte/mbrtoc16.c b/src/multibyte/mbrtoc16.c new file mode 100644 index 0000000..765ff90 --- /dev/null +++ b/src/multibyte/mbrtoc16.c @@ -0,0 +1,30 @@ +#include <uchar.h> +#include <wchar.h> + +size_t mbrtoc16(char16_t *restrict pc16, const char *restrict s, size_t n, mbstate_t *restrict ps) +{ + static unsigned internal_state; + if (!ps) ps = (void *)&internal_state; + unsigned *pending = (unsigned *)ps; + + if (!s) return mbrtoc16(0, "", 1, ps); + + /* mbrtowc states for partial UTF-8 characters have the high bit set; + * we use nonzero states without high bit for pending surrogates. */ + if ((int)*pending > 0) { + if (pc16) *pc16 = *pending; + *pending = 0; + return -3; + } + + wchar_t wc; + size_t ret = mbrtowc(&wc, s, n, ps); + if (ret <= 4) { + if (wc >= 0x10000) { + *pending = (wc & 0x3ff) + 0xdc00; + wc = 0xd7c0 + (wc >> 10); + } + if (pc16) *pc16 = wc; + } + return ret; +} |