Struct Utf16ByteCodec 

pub struct Utf16ByteCodec { /* private fields */ }

Combined byte-serialized UTF-16 codec.

The codec uses one configured byte order for both decoding and encoding. It does not detect, consume, or emit a BOM automatically; callers should use crate::UnicodeBom when a byte stream may carry an explicit BOM.

Examples

use qubit_codec_text::{
    ByteOrder,
    CharsetCodec,
    CharsetEncodeProbe,
    Codec,
    Charset,
    Utf16,
    Utf16ByteCodec,
};

let codec = Utf16ByteCodec::new(ByteOrder::LittleEndian);
assert_eq!(Charset::UTF_16LE, codec.charset());
assert_eq!(Utf16::MAX_BYTES_PER_CHAR, codec.max_units_per_value().get());

let mut output = [0_u8; Utf16::MAX_BYTES_PER_CHAR];
let written = codec.encode_len('😀', 0).expect("mappable");
unsafe {
    codec.encode_unchecked(&'😀', &mut output, 0).expect("buffer fits");
}
let (value, consumed) = unsafe {
    codec.decode_unchecked(&output[..written], 0).expect("valid UTF-16LE")
};
assert_eq!(('😀', written), (value, consumed.get()));

Implementations

impl Utf16ByteCodec

pub const fn new(byte_order: ByteOrder) -> Self

Creates a byte-serialized UTF-16 codec.

Parameters

• byte_order: The byte order used by the byte buffer.

Returns

Returns a UTF-16 byte codec.

pub const fn byte_order(self) -> ByteOrder

Returns the configured byte order.

Returns

Returns the byte order used by this codec.

pub const fn charset(self) -> Charset

Returns the fixed-endian UTF-16 charset descriptor.

Returns

Returns Charset::UTF_16LE or Charset::UTF_16BE according to this codec’s configured byte order.

Trait Implementations

impl CharsetCodec for Utf16ByteCodec

fn charset(&self) -> Charset

Returns the fixed-endian UTF-16 charset for the configured byte order.

Returns

Returns Charset::UTF_16BE when configured with ByteOrder::BigEndian, otherwise Charset::UTF_16LE.

impl CharsetEncodeProbe for Utf16ByteCodec

fn encode_len(&self, ch: char, _index: usize) -> CharsetEncodeResult<usize>

Encodes one Unicode scalar value into UTF-16 bytes at index.

Arguments

• ch - The Unicode scalar value to encode.
• index - Input character index used for error context.

Returns

Ok(usize) with the required bytes (2 for BMP and 4 for supplementary).

impl Clone for Utf16ByteCodec

fn clone(&self) -> Utf16ByteCodec

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Codec for Utf16ByteCodec

type Value = char

Logical value decoded from or encoded into the buffer.

type Unit = u8

Buffer unit used by the encoded representation.

type DecodeError = CharsetDecodeError

Error reported when decoding malformed units.

type EncodeError = CharsetEncodeError

Error reported when encoding an unsupported value.

fn min_units_per_value(&self) -> NonZeroUsize

Returns the minimum possible unit count for one encoded value.

fn max_units_per_value(&self) -> NonZeroUsize

Returns the maximum non-zero unit count needed to encode or decode one value.

unsafe fn decode_unchecked( &self, input: &[u8], index: usize, ) -> CharsetDecodeResult<(char, NonZeroUsize)>

Decodes one value from input starting at index.

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

Encodes one borrowed value into output starting at index.

impl Copy for Utf16ByteCodec

impl Debug for Utf16ByteCodec

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

Formats the value using the given formatter.

impl Eq for Utf16ByteCodec

impl PartialEq for Utf16ByteCodec

fn eq(&self, other: &Utf16ByteCodec) -> 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 StructuralPartialEq for Utf16ByteCodec