NAME

src/encodings/utf8.c - UTF-8 encoding

DESCRIPTION

UTF-8 (http://www.utf-8.com/).

Functions

utf8_characters

Returns the number of characters in the byte_len bytes from *ptr.

utf8_decode

Returns the integer for the UTF-8 character found at *ptr.

utf8_encode

Returns the UTF-8 encoding of integer c.

utf8_skip_forward

Moves ptr n characters forward.

utf8_skip_backward

Moves ptr n characters back.

Iterator Functions

utf8_decode_and_advance

The UTF-8 implementation of the string iterator's get_and_advance function.

*/

static UINTVAL utf8_decode_and_advance(PARROT_INTERP, NOTNULL(String_iter *i)) { const utf8_t *u8ptr = (utf8_t *)((char *)i->str->strstart + i->bytepos); UINTVAL c = *u8ptr;

    if (UTF8_IS_START(c)) {
        UINTVAL len = UTF8SKIP(u8ptr);

        c &= UTF8_START_MASK(len);
        i->bytepos += len;
        for (len--; len; len--) {
            u8ptr++;
            if (!UTF8_IS_CONTINUATION(*u8ptr)) {
                real_exception(interp, NULL, MALFORMED_UTF8, "Malformed UTF-8 string\n");
            }
            c = UTF8_ACCUMULATE(c, *u8ptr);
        }

        if (UNICODE_IS_SURROGATE(c)) {
            real_exception(interp, NULL, MALFORMED_UTF8, "Surrogate in UTF-8 string\n");
        }
    }
    else if (!UNICODE_IS_INVARIANT(c)) {
        real_exception(interp, NULL, MALFORMED_UTF8, "Malformed UTF-8 string\n");
    }
    else {
        i->bytepos++;
    }

    i->charpos++;
    return c;
}

/*

utf8_encode_and_advance

The UTF-8 implementation of the string iterator's set_and_advance function.

utf8_set_position

The UTF-8 implementation of the string iterator's set_position function.

to_encoding

TODO: Not yet documented!!!

get_codepoint

TODO: Not yet documented!!!

set_codepoint

TODO: Not yet documented!!!

get_byte

TODO: Not yet documented!!!

set_byte

TODO: Not yet documented!!!

get_codepoints

TODO: Not yet documented!!!

get_bytes

TODO: Not yet documented!!!

get_codepoints_inplace

TODO: Not yet documented!!!

get_bytes_inplace

TODO: Not yet documented!!!

set_codepoints

TODO: Not yet documented!!!

set_bytes

TODO: Not yet documented!!!

become_encoding

TODO: Not yet documented!!!

codepoints

TODO: Not yet documented!!!

bytes

TODO: Not yet documented!!!

iter_init

TODO: Not yet documented!!!

Parrot_encoding_utf8_init

TODO: Not yet documented!!!

SEE ALSO

src/encodings/fixed_8.c, src/string.c, include/parrot/string.h, docs/string.pod.