each_codepoint()
public
Passes the Integer ordinal of each character in str, also known as
a codepoint when applied to Unicode strings to the given block.
"hello\u0639".each_codepoint {|c| print c, ' ' }
produces:
104 101 108 108 111 1593
static VALUE
rb_str_each_codepoint(VALUE str)
{
long len;
int n;
unsigned int c;
const char *ptr, *end;
rb_encoding *enc;
if (single_byte_optimizable(str)) return rb_str_each_byte(str);
RETURN_ENUMERATOR(str, 0, 0);
ptr = RSTRING_PTR(str);
len = RSTRING_LEN(str);
end = RSTRING_END(str);
enc = STR_ENC_GET(str);
while (ptr < end) {
c = rb_enc_codepoint(ptr, end, enc);
n = rb_enc_codelen(c, enc);
rb_yield(UINT2NUM(c));
ptr += n;
}
return str;
}