Struct Utf8Codec 

pub struct Utf8Codec;

UTF-8 byte-buffer charset codec.

Examples

use qubit_text_codec::{
    CharsetCodec,
    DecodeStatus,
    Charset,
    Utf8,
    Utf8Codec,
};

let codec = Utf8Codec;
assert_eq!(Charset::UTF_8, codec.charset());
assert_eq!(Utf8::MAX_UNITS_PER_CHAR, codec.max_units_per_char());

let mut output = [0_u8; Utf8::MAX_BYTES_PER_CHAR];
let written = codec.encode_one('é', &mut output, 0).expect("buffer fits");
assert_eq!(
    DecodeStatus::Complete {
        value: 'é',
        consumed: written,
    },
    codec.decode_one(&output[..written], 0).expect("valid UTF-8"),
);

Implementations

impl Utf8Codec

pub const fn charset(self) -> Charset

Returns the UTF-8 encoding descriptor.

Returns

Returns Charset::UTF_8.

pub const fn max_units_per_char(self) -> usize

Returns the maximum number of UTF-8 bytes needed for one character.

Returns

Returns Utf8::MAX_UNITS_PER_CHAR.

Trait Implementations

impl CharsetCodec for Utf8Codec

fn charset(&self) -> Charset

Returns UTF-8 charset descriptor.

Returns

Returns Charset::UTF_8.

fn max_units_per_char(&self) -> usize

Returns the maximum number of UTF-8 bytes for one character.

Returns

Returns Utf8::MAX_UNITS_PER_CHAR.

fn decode_one( &self, input: &[u8], index: usize, ) -> CharsetDecodeResult<DecodeStatus>

Decodes one UTF-8 character from a byte prefix.

Arguments

• input - UTF-8 byte slice.
• index - Start offset for decoding; must satisfy index <= input.len().

Returns

• Ok(DecodeStatus::NeedMore { required, available }) for partial input.
• Ok(DecodeStatus::Complete { value, consumed }) for a decoded scalar value.

Errors

• crate::CharsetDecodeErrorKind::MalformedSequence for invalid UTF-8 byte sequence.

fn encode_one( &self, ch: char, output: &mut [u8], index: usize, ) -> CharsetEncodeResult<usize>

Encodes one Unicode scalar value into UTF-8 bytes at index.

Arguments

• ch - The Unicode scalar value to encode.
• output - Destination byte buffer.
• index - Start offset where bytes are written; must satisfy index <= output.len().

Returns

Ok(usize) with encoded bytes (1..=4).

Errors

• crate::CharsetEncodeErrorKind::BufferTooSmall if output has insufficient bytes from index.

type Unit = u8

Storage unit used by the encoded representation.

impl Clone for Utf8Codec

fn clone(&self) -> Utf8Codec

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Utf8Codec

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Utf8Codec

fn default() -> Utf8Codec

Returns the “default value” for a type.

impl Hash for Utf8Codec

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for Utf8Codec

fn eq(&self, other: &Utf8Codec) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for Utf8Codec

impl Eq for Utf8Codec

impl StructuralPartialEq for Utf8Codec