Replace the generated C++ legacy codec implementations with a small Rust wrapper around encoding_rs. This keeps the existing LibTextCodec API while moving label lookup, legacy decode/encode, validation, and streaming decoder state to Rust. The generated index data and generator are no longer needed. It also fixes several TextDecoder EOF cases due to a more correct implementation. encoding_rs finalizes decoders according to the Encoding Standard, so incomplete UTF-8/Big5 tails and malformed UTF-16 surrogate tails produce the required single replacement at end-of-queue instead of being dropped, buffered, or double-counted by our old hand-written decoders.
29 lines
677 B
C++
29 lines
677 B
C++
/*
|
|
* Copyright (c) 2024, Ben Jilks <benjyjilks@gmail.com>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <AK/Forward.h>
|
|
#include <AK/Function.h>
|
|
#include <LibTextCodec/Export.h>
|
|
#include <LibTextCodec/Forward.h>
|
|
|
|
namespace TextCodec {
|
|
|
|
class TEXTCODEC_API Encoder {
|
|
public:
|
|
virtual ErrorOr<void> process(Utf8View, Function<ErrorOr<void>(u8)> on_byte, Function<ErrorOr<void>(u32)> on_error) = 0;
|
|
|
|
protected:
|
|
virtual ~Encoder() = default;
|
|
};
|
|
|
|
TEXTCODEC_API Optional<Encoder&> encoder_for_exact_name(StringView encoding);
|
|
TEXTCODEC_API Optional<Encoder&> encoder_for(StringView label);
|
|
|
|
TEXTCODEC_API ByteString isomorphic_encode(StringView);
|
|
|
|
}
|