deepdrft/DeepDrftContent/Processors/AudioProcessor.cs

using DeepDrftContent.FileDatabase.Models;

namespace DeepDrftContent.Processors;

/// <summary>
/// Service for processing audio files and extracting metadata
/// </summary>
public class AudioProcessor
{
    // Header parsing never needs the audio body. Read the file in 64 KB steps until the data-chunk
    // header is locatable, capping the window so a pathological file with an enormous pre-data header
    // cannot drive an unbounded allocation — such a file simply falls through to default metadata and
    // passthrough storage, the same outcome as any unparseable WAV.
    private const int HeaderWindowStep = 64 * 1024;
    private const int HeaderWindowCap = 8 * 1024 * 1024;

    /// <summary>
    /// Processes a WAV file into a <see cref="ProcessedAudio"/> store plan: extracts metadata from a
    /// bounded header window (never the whole file) and returns a streamed writer for the canonical
    /// vault bytes. Standard PCM is stored verbatim (passthrough copy); EXTENSIBLE-PCM / IEEE-float /
    /// padded-container WAVs are normalized to a plain 44-byte standard-PCM WAV, written progressively
    /// so the vault only ever holds a format the streaming pipeline already handles.
    /// </summary>
    /// <param name="filePath">Path to the WAV file</param>
    public async Task<ProcessedAudio?> ProcessWavFileAsync(string filePath, CancellationToken cancellationToken = default)
    {
        if (!File.Exists(filePath))
        {
            throw new FileNotFoundException($"WAV file not found: {filePath}");
        }

        if (!Path.GetExtension(filePath).Equals(".wav", StringComparison.OrdinalIgnoreCase))
        {
            throw new ArgumentException("File must be a WAV file", nameof(filePath));
        }

        try
        {
            var fileLength = new FileInfo(filePath).Length;
            var window = await ReadWavHeaderWindowAsync(filePath, cancellationToken);
            var wavInfo = ExtractWavMetadata(window);

            if (!wavInfo.IsExtensible)
            {
                // Standard PCM (or the default-fallback path, which reports IsExtensible = false):
                // the source bytes are already a format the pipeline handles, so store them verbatim.
                return ProcessedAudio.Passthrough(filePath, ".wav", wavInfo.Duration, wavInfo.Bitrate, fileLength);
            }

            // EXTENSIBLE → streamed normalization. The output data size is derivable from the source
            // data size alone (no body read needed): verbatim keeps it, float drops 1 byte per sample
            // (4→3), padded keeps only the valid bytes per container sample.
            var dataStart = (long)wavInfo.DataChunkPos + 8;
            var available = fileLength - dataStart;
            var srcDataSize = Math.Min((long)wavInfo.DataSize, available);

            NormalizeMode mode;
            int outBitsPerSample;
            long outDataSize;
            int containerBytes = 0;
            int validBytes = 0;
            if (wavInfo.IsFloat)
            {
                mode = NormalizeMode.Float;
                outBitsPerSample = 24;
                outDataSize = (srcDataSize / 4) * 3;
            }
            else if (wavInfo.IsPaddedContainer)
            {
                mode = NormalizeMode.Padded;
                outBitsPerSample = wavInfo.BitsPerSample;
                containerBytes = wavInfo.ContainerBitsPerSample / 8;
                validBytes = wavInfo.BitsPerSample / 8;
                outDataSize = (srcDataSize / containerBytes) * validBytes;
            }
            else
            {
                mode = NormalizeMode.Verbatim;
                outBitsPerSample = wavInfo.BitsPerSample;
                outDataSize = srcDataSize;
            }

            var channels = wavInfo.Channels;
            var sampleRate = wavInfo.SampleRate;

            return new ProcessedAudio(
                ".wav", wavInfo.Duration, wavInfo.Bitrate, 44 + outDataSize,
                (destination, ct) => WriteNormalizedWavAsync(
                    filePath, dataStart, srcDataSize, channels, sampleRate, outBitsPerSample,
                    outDataSize, mode, containerBytes, validBytes, destination, ct));
        }
        catch (Exception ex) when (ex is not OperationCanceledException)
        {
            throw new InvalidOperationException($"Failed to process WAV file: {ex.Message}", ex);
        }
    }

    /// <summary>
    /// Reads only enough of the file to contain the fmt chunk and the data chunk's 8-byte header, so
    /// metadata parsing never loads the (potentially ~GB) audio body. Grows the window in 64 KB steps
    /// until the data chunk is locatable or EOF/<see cref="HeaderWindowCap"/> is hit.
    /// </summary>
    private static async Task<byte[]> ReadWavHeaderWindowAsync(string filePath, CancellationToken ct)
    {
        await using var fs = new FileStream(
            filePath, FileMode.Open, FileAccess.Read, FileShare.Read,
            bufferSize: HeaderWindowStep, useAsync: true);

        using var ms = new MemoryStream();
        var buffer = new byte[HeaderWindowStep];
        while (ms.Length < HeaderWindowCap)
        {
            var read = await fs.ReadAsync(buffer, ct);
            if (read == 0)
                break;
            ms.Write(buffer, 0, read);

            // FindChunk returns -1 on a partial window (the data chunk isn't reachable yet), so keep
            // reading until it is found or the cap/EOF is hit. On normal files the data chunk header
            // sits within the first 64 KB, so this loop runs exactly once.
            var soFar = ms.ToArray();
            if (FindChunk(soFar, "data") >= 0)
                return soFar;
        }

        return ms.ToArray();
    }

    /// <summary>
    /// Writes a normalized standard-PCM WAV to <paramref name="destination"/>: the 44-byte header
    /// followed by the data region streamed from the source in bounded, sample-aligned chunks. No
    /// whole-file buffer is ever held — peak memory is O(chunk), independent of duration.
    /// </summary>
    private async Task WriteNormalizedWavAsync(
        string sourcePath, long dataStart, long srcDataSize,
        int channels, int sampleRate, int outBitsPerSample, long outDataSize,
        NormalizeMode mode, int containerBytes, int validBytes,
        Stream destination, CancellationToken ct)
    {
        var header = BuildStandardPcmHeader(channels, sampleRate, outBitsPerSample, outDataSize);
        await destination.WriteAsync(header, ct);

        await using var src = new FileStream(
            sourcePath, FileMode.Open, FileAccess.Read, FileShare.Read,
            bufferSize: 81920, useAsync: true);
        src.Seek(dataStart, SeekOrigin.Begin);

        switch (mode)
        {
            case NormalizeMode.Verbatim:
                await CopyBoundedAsync(src, destination, srcDataSize, ct);
                break;
            case NormalizeMode.Float:
                // Each 4-byte float sample becomes 3 bytes of 24-bit PCM.
                await TransformBoundedAsync(src, destination, srcDataSize, unit: 4,
                    transform: (buf, len) => ConvertFloatTo24BitPcm(buf, 0, len), ct);
                break;
            case NormalizeMode.Padded:
                await TransformBoundedAsync(src, destination, srcDataSize, unit: containerBytes,
                    transform: (buf, len) => RepackPaddedContainer(buf, 0, len, containerBytes * 8, validBytes * 8), ct);
                break;
        }
    }

    /// <summary>Bounded copy of exactly <paramref name="totalBytes"/> from src to dest.</summary>
    private static async Task CopyBoundedAsync(Stream src, Stream dest, long totalBytes, CancellationToken ct)
    {
        var buffer = new byte[81920];
        var remaining = totalBytes;
        while (remaining > 0)
        {
            var want = (int)Math.Min(buffer.Length, remaining);
            var read = await src.ReadAsync(buffer.AsMemory(0, want), ct);
            if (read == 0)
                break;
            await dest.WriteAsync(buffer.AsMemory(0, read), ct);
            remaining -= read;
        }
    }

    /// <summary>
    /// Streams <paramref name="totalBytes"/> of source data through <paramref name="transform"/> in
    /// sample-aligned chunks, writing each transformed chunk to <paramref name="dest"/>. The read
    /// buffer is a multiple of <paramref name="unit"/>; leftover bytes that do not complete a sample
    /// are carried into the next read, and a final partial sample is dropped (matching the
    /// whole-buffer transforms' integer-division behavior).
    /// </summary>
    private static async Task TransformBoundedAsync(
        Stream src, Stream dest, long totalBytes, int unit,
        Func<byte[], int, byte[]> transform, CancellationToken ct)
    {
        var bufLen = Math.Max(unit, (81920 / unit) * unit);
        var buffer = new byte[bufLen];
        var remaining = totalBytes;
        var carried = 0;
        while (remaining > 0)
        {
            var want = (int)Math.Min(bufLen - carried, remaining);
            if (want == 0)
                break;
            var read = await src.ReadAsync(buffer.AsMemory(carried, want), ct);
            if (read == 0)
                break;
            remaining -= read;

            var filled = carried + read;
            var whole = (filled / unit) * unit;
            if (whole > 0)
            {
                var output = transform(buffer, whole);
                await dest.WriteAsync(output, ct);
            }

            carried = filled - whole;
            if (carried > 0)
                Array.Copy(buffer, whole, buffer, 0, carried);
        }
    }

    private enum NormalizeMode
    {
        /// <summary>Sample bytes already standard PCM (EXTENSIBLE-PCM, depth == container width).</summary>
        Verbatim,
        /// <summary>IEEE float samples converted to 24-bit PCM.</summary>
        Float,
        /// <summary>Padded container (e.g. 24-in-32) re-packed to the valid depth.</summary>
        Padded
    }

    /// <summary>
    /// Extracts the raw PCM data region and format parameters from a WAV buffer, reusing the
    /// same chunk-walk and validation as metadata extraction. Returns null if the buffer is not
    /// a valid PCM WAV (callers treat a null as "no profile computable" and continue) — unlike
    /// <see cref="ExtractWavMetadata"/>, this does NOT fall back to synthetic defaults, because a
    /// loudness profile over fabricated silence would be misleading.
    /// </summary>
    public PcmData? TryExtractPcm(ReadOnlySpan<byte> buffer)
    {
        // Copy the span to an array so the existing array-based parsers can be reused. The PCM
        // slice returned is a view over this array (no second copy of the data region).
        var bytes = buffer.ToArray();

        var validation = ValidateWavStructure(bytes);
        if (!validation.IsValid)
        {
            return null;
        }

        // Float and padded-container EXTENSIBLE require a sample-level transform to become integer PCM.
        // TryExtractPcm feeds loudness analysis, not storage, and must not hand back float bytes
        // mislabeled as integer PCM — out of scope here, so treat them as "no profile computable".
        if (validation.IsFloat)
        {
            return null;
        }

        WavMetadata metadata;
        try
        {
            metadata = ParseWavMetadata(bytes, validation);
            ValidateAudioParameters(metadata);
            if (metadata.IsPaddedContainer)
            {
                return null;
            }
        }
        catch
        {
            return null;
        }

        // Data bytes begin 8 past the "data" chunk id (4 id + 4 size). Clamp the declared size to
        // what is actually present — some encoders write a size that overshoots the file.
        var dataStart = validation.DataChunkPos + 8;
        if (dataStart > bytes.Length)
        {
            return null;
        }

        var available = bytes.Length - dataStart;
        var dataLength = Math.Min(metadata.DataSize, available);
        if (dataLength <= 0)
        {
            return null;
        }

        var pcm = new ReadOnlyMemory<byte>(bytes, dataStart, dataLength);
        return new PcmData(pcm, metadata.Channels, metadata.SampleRate, metadata.BitsPerSample);
    }

    /// <summary>
    /// Reads only the WAV header region from <paramref name="stream"/> (a bounded window, never the
    /// audio body) and returns where the PCM data region begins, how long it is, and the format
    /// parameters needed to decode it — the streaming counterpart of <see cref="TryExtractPcm"/>. The
    /// data length is clamped against <paramref name="totalFileLength"/> (the true backing-file size),
    /// so the caller streams exactly the present PCM. Returns null for the same inputs
    /// <see cref="TryExtractPcm"/> rejects — non-WAV bytes (mp3/flac), float, and padded-container
    /// EXTENSIBLE — so the caller treats null as "no profile computable" and continues gracefully.
    ///
    /// <paramref name="stream"/> must be positioned at the start; on return its position is past the
    /// header window (the caller seeks to <c>DataStart</c> before streaming the body). No whole-file
    /// buffer is allocated — peak memory is the bounded header window.
    /// </summary>
    public async Task<WavPcmStreamInfo?> TryReadPcmStreamInfoAsync(
        Stream stream, long totalFileLength, CancellationToken cancellationToken = default)
    {
        var window = await ReadWavHeaderWindowAsync(stream, cancellationToken);
        if (window is null)
        {
            return null;
        }

        var validation = ValidateWavStructure(window);
        if (!validation.IsValid || validation.IsFloat)
        {
            return null;
        }

        WavMetadata metadata;
        try
        {
            metadata = ParseWavMetadata(window, validation);
            ValidateAudioParameters(metadata);
            if (metadata.IsPaddedContainer)
            {
                return null;
            }
        }
        catch
        {
            return null;
        }

        long dataStart = validation.DataChunkPos + 8;
        if (dataStart > totalFileLength)
        {
            return null;
        }

        var available = totalFileLength - dataStart;
        var dataLength = Math.Min((long)metadata.DataSize, available);
        if (dataLength <= 0)
        {
            return null;
        }

        return new WavPcmStreamInfo(
            dataStart, dataLength, metadata.Channels, metadata.SampleRate, metadata.BitsPerSample);
    }

    /// <summary>
    /// Reads enough of <paramref name="stream"/> to contain the fmt chunk and the data chunk's 8-byte
    /// header, growing in 64 KB steps until the data chunk is locatable or EOF / the
    /// <see cref="HeaderWindowCap"/> is reached. Bails after the first read when the bytes are not a
    /// RIFF/WAVE container, so a non-WAV stream (mp3/flac) costs one read, not the full cap. Returns
    /// null only when nothing could be read.
    /// </summary>
    private static async Task<byte[]?> ReadWavHeaderWindowAsync(Stream stream, CancellationToken ct)
    {
        using var ms = new MemoryStream();
        var buffer = new byte[HeaderWindowStep];
        while (ms.Length < HeaderWindowCap)
        {
            var read = await stream.ReadAsync(buffer, ct);
            if (read == 0)
                break;
            ms.Write(buffer, 0, read);

            var soFar = ms.ToArray();

            // Early-out for non-WAV input: once at least the 12-byte RIFF/WAVE preamble is in hand,
            // a missing signature means this will never be a WAV — stop rather than read to the cap.
            if (soFar.Length >= 12 && !HasRiffWaveSignature(soFar))
                return soFar;

            // FindChunk returns -1 until the data chunk header is fully in the window; on a normal
            // file it sits within the first 64 KB so this loop runs exactly once.
            if (FindChunk(soFar, "data") >= 0)
                return soFar;
        }

        return ms.Length > 0 ? ms.ToArray() : null;
    }

    private static bool HasRiffWaveSignature(byte[] buffer) =>
        buffer.Length >= 12
        && System.Text.Encoding.ASCII.GetString(buffer, 0, 4) == "RIFF"
        && System.Text.Encoding.ASCII.GetString(buffer, 8, 4) == "WAVE";

    /// <summary>
    /// Extracts metadata from WAV file buffer with comprehensive validation
    /// </summary>
    private WavMetadata ExtractWavMetadata(byte[] buffer)
    {
        try
        {
            var validationResult = ValidateWavStructure(buffer);
            if (!validationResult.IsValid)
            {
                throw new InvalidDataException($"WAV validation failed: {validationResult.ErrorMessage}");
            }

            var metadata = ParseWavMetadata(buffer, validationResult);
            ValidateAudioParameters(metadata);
            
            return metadata;
        }
        catch (Exception ex)
        {
            Console.WriteLine($"Warning: WAV parsing failed, using defaults: {ex.Message}");
            return GetDefaultWavMetadata();
        }
    }
    
    /// <summary>
    /// Validates WAV file structure and returns parsing information
    /// </summary>
    private WavValidationResult ValidateWavStructure(byte[] buffer)
    {
        if (buffer.Length < 44)
        {
            return new WavValidationResult { IsValid = false, ErrorMessage = "File too short" };
        }

        // Validate RIFF signature
        var riffSignature = System.Text.Encoding.ASCII.GetString(buffer, 0, 4);
        if (riffSignature != "RIFF")
        {
            return new WavValidationResult { IsValid = false, ErrorMessage = "Invalid RIFF signature" };
        }

        // Validate WAVE signature
        var waveSignature = System.Text.Encoding.ASCII.GetString(buffer, 8, 4);
        if (waveSignature != "WAVE")
        {
            return new WavValidationResult { IsValid = false, ErrorMessage = "Invalid WAVE signature" };
        }

        // Find and validate fmt chunk
        var fmtChunkPos = FindChunk(buffer, "fmt ");
        if (fmtChunkPos == -1)
        {
            return new WavValidationResult { IsValid = false, ErrorMessage = "Missing fmt chunk" };
        }

        var fmtChunkSize = BitConverter.ToUInt32(buffer, fmtChunkPos + 4);
        if (fmtChunkSize < 16)
        {
            return new WavValidationResult { IsValid = false, ErrorMessage = "fmt chunk too small" };
        }

        // Validate audio format. Standard PCM (1) is accepted directly. WAVE_FORMAT_EXTENSIBLE
        // (0xFFFE) is accepted when its SubFormat GUID indicates PCM (0x0001) or IEEE float
        // (0x0003). PCM sample data is byte-identical to standard PCM; float data is converted to
        // 24-bit PCM downstream. Either way the vault only ever holds standard PCM.
        var audioFormat = BitConverter.ToUInt16(buffer, fmtChunkPos + 8);
        var isExtensible = false;
        var isFloat = false;
        if (audioFormat == 0xFFFE)
        {
            // EXTENSIBLE requires the full extension: 16 base + 2 cbSize + 22 extension = 40 bytes.
            if (fmtChunkSize < 40)
            {
                return new WavValidationResult { IsValid = false, ErrorMessage = "Invalid data: EXTENSIBLE fmt chunk too small" };
            }

            if (fmtChunkPos + 8 + 40 > buffer.Length)
            {
                return new WavValidationResult { IsValid = false, ErrorMessage = "Invalid data: EXTENSIBLE fmt chunk extends past end of file" };
            }

            // SubFormat GUID begins 24 bytes into the fmt chunk data (fmtChunkPos + 8 + 24). Its
            // first two bytes are the little-endian format tag: 0x0001 == WAVE_FORMAT_PCM,
            // 0x0003 == WAVE_FORMAT_IEEE_FLOAT.
            var subFormatPos = fmtChunkPos + 8 + 24;
            var subFormatTag = BitConverter.ToUInt16(buffer, subFormatPos);
            if (subFormatTag == 0x0001)
            {
                isExtensible = true;
            }
            else if (subFormatTag == 0x0003)
            {
                isExtensible = true;
                isFloat = true;
            }
            else
            {
                return new WavValidationResult { IsValid = false, ErrorMessage = "Invalid data: EXTENSIBLE SubFormat is neither PCM nor IEEE float" };
            }
        }
        else if (audioFormat != 1)
        {
            return new WavValidationResult { IsValid = false, ErrorMessage = "Only PCM format supported" };
        }

        // Find data chunk
        var dataChunkPos = FindChunk(buffer, "data");
        if (dataChunkPos == -1)
        {
            return new WavValidationResult { IsValid = false, ErrorMessage = "Missing data chunk" };
        }

        return new WavValidationResult
        {
            IsValid = true,
            FmtChunkPos = fmtChunkPos,
            DataChunkPos = dataChunkPos,
            IsExtensible = isExtensible,
            IsFloat = isFloat
        };
    }
    
    /// <summary>
    /// Parses WAV metadata from validated buffer
    /// </summary>
    private WavMetadata ParseWavMetadata(byte[] buffer, WavValidationResult validation)
    {
        var channels = BitConverter.ToUInt16(buffer, validation.FmtChunkPos + 10);
        var sampleRate = BitConverter.ToUInt32(buffer, validation.FmtChunkPos + 12);
        var byteRate = BitConverter.ToUInt32(buffer, validation.FmtChunkPos + 16);
        var blockAlign = BitConverter.ToUInt16(buffer, validation.FmtChunkPos + 20);
        var bitsPerSample = BitConverter.ToUInt16(buffer, validation.FmtChunkPos + 22);
        var dataSize = BitConverter.ToUInt32(buffer, validation.DataChunkPos + 4);

        // For EXTENSIBLE the offset-22 field is the container width; the true sample depth lives in
        // wValidBitsPerSample (fmtChunkPos + 8 + 18). They usually match (Bandcamp 24-bit = 24/24)
        // but the valid bits are authoritative for the normalized header and metadata. When they
        // differ (e.g. 24-bit valid in a 32-bit container) we keep the container width separately so
        // ValidateAudioParameters can reconcile against the header BlockAlign and NormalizeToStandardPcm
        // can re-pack the padded frames.
        var containerBitsPerSample = 0;
        if (validation.IsExtensible)
        {
            var validBits = BitConverter.ToUInt16(buffer, validation.FmtChunkPos + 8 + 18);
            if (validBits != bitsPerSample)
            {
                containerBitsPerSample = bitsPerSample;
            }
            bitsPerSample = validBits;
        }

        var duration = byteRate > 0 ? (double)dataSize / byteRate : 0.0;
        var bitrate = (int)((sampleRate * channels * bitsPerSample) / 1000);

        return new WavMetadata
        {
            Duration = duration,
            Bitrate = bitrate,
            SampleRate = (int)sampleRate,
            Channels = channels,
            BitsPerSample = bitsPerSample,
            ContainerBitsPerSample = containerBitsPerSample,
            BlockAlign = blockAlign,
            DataSize = (int)dataSize,
            DataChunkPos = validation.DataChunkPos,
            IsExtensible = validation.IsExtensible,
            IsFloat = validation.IsFloat
        };
    }
    
    /// <summary>
    /// Validates audio parameters for reasonableness
    /// </summary>
    private void ValidateAudioParameters(WavMetadata metadata)
    {
        var validSampleRates = new[] { 8000, 11025, 16000, 22050, 44100, 48000, 88200, 96000, 176400, 192000 };
        var validBitDepths = new[] { 8, 16, 24, 32 };
        
        if (metadata.Channels < 1 || metadata.Channels > 8)
        {
            throw new InvalidDataException($"Invalid channel count: {metadata.Channels}");
        }
        
        if (!validSampleRates.Contains(metadata.SampleRate))
        {
            throw new InvalidDataException($"Unsupported sample rate: {metadata.SampleRate}");
        }
        
        if (!validBitDepths.Contains(metadata.BitsPerSample))
        {
            throw new InvalidDataException($"Unsupported bit depth: {metadata.BitsPerSample}");
        }
        
        // The header BlockAlign reflects the container width, not the valid bit depth. For a padded
        // EXTENSIBLE container (e.g. 24-in-32) the container width is authoritative for this check;
        // NormalizeToStandardPcm re-packs the frames down to the valid depth afterwards.
        var blockAlignBits = metadata.IsPaddedContainer ? metadata.ContainerBitsPerSample : metadata.BitsPerSample;
        var expectedBlockAlign = metadata.Channels * (blockAlignBits / 8);
        if (metadata.BlockAlign != expectedBlockAlign)
        {
            throw new InvalidDataException($"Invalid block align: expected {expectedBlockAlign}, got {metadata.BlockAlign}");
        }
    }
    
    /// <summary>
    /// Builds the canonical 44-byte standard-PCM WAV header (audioFormat = 1) for a normalized stream.
    /// The body is written separately so no whole-file buffer is allocated; this only emits the header
    /// the streaming pipeline expects, reporting the valid (post-normalization) bit depth.
    /// </summary>
    private static byte[] BuildStandardPcmHeader(int channels, int sampleRate, int outBitsPerSample, long dataSize)
    {
        const int headerSize = 44;
        var result = new byte[headerSize];

        var blockAlign = (ushort)(channels * (outBitsPerSample / 8));
        var byteRate = (uint)(sampleRate * blockAlign);

        // RIFF header
        System.Text.Encoding.ASCII.GetBytes("RIFF").CopyTo(result, 0);
        BitConverter.GetBytes((uint)(36 + dataSize)).CopyTo(result, 4);
        System.Text.Encoding.ASCII.GetBytes("WAVE").CopyTo(result, 8);

        // fmt chunk (standard 16-byte PCM)
        System.Text.Encoding.ASCII.GetBytes("fmt ").CopyTo(result, 12);
        BitConverter.GetBytes((uint)16).CopyTo(result, 16);
        BitConverter.GetBytes((ushort)1).CopyTo(result, 20); // audioFormat = PCM
        BitConverter.GetBytes((ushort)channels).CopyTo(result, 22);
        BitConverter.GetBytes((uint)sampleRate).CopyTo(result, 24);
        BitConverter.GetBytes(byteRate).CopyTo(result, 28);
        BitConverter.GetBytes(blockAlign).CopyTo(result, 32);
        BitConverter.GetBytes((ushort)outBitsPerSample).CopyTo(result, 34);

        // data chunk
        System.Text.Encoding.ASCII.GetBytes("data").CopyTo(result, 36);
        BitConverter.GetBytes((uint)dataSize).CopyTo(result, 40);

        return result;
    }

    /// <summary>
    /// Converts 32-bit little-endian IEEE float samples (range [-1.0, 1.0]) to 24-bit signed PCM.
    /// Each 4-byte source sample becomes 3 little-endian output bytes; output size is 3/4 of input.
    /// Trailing bytes that do not form a complete 4-byte sample are ignored.
    /// </summary>
    private static byte[] ConvertFloatTo24BitPcm(byte[] buffer, int dataStart, int dataSize)
    {
        var sampleCount = dataSize / 4;
        var output = new byte[sampleCount * 3];

        for (int i = 0; i < sampleCount; i++)
        {
            var sample = BitConverter.ToSingle(buffer, dataStart + i * 4);
            var value = (int)(sample * 8388607.0);
            value = Math.Clamp(value, -8388608, 8388607);

            var o = i * 3;
            output[o] = (byte)(value & 0xFF);
            output[o + 1] = (byte)((value >> 8) & 0xFF);
            output[o + 2] = (byte)((value >> 16) & 0xFF);
        }

        return output;
    }

    /// <summary>
    /// Strips container padding from a padded-container EXTENSIBLE WAV (e.g. 24-bit valid samples
    /// stored in 32-bit containers), keeping only the lowest <paramref name="validBits"/> bytes of
    /// each little-endian sample. Output size is (validBits/containerBits) of input.
    /// Trailing bytes that do not form a complete container sample are ignored.
    /// </summary>
    private static byte[] RepackPaddedContainer(byte[] buffer, int dataStart, int dataSize, int containerBits, int validBits)
    {
        var containerBytes = containerBits / 8;
        var validBytes = validBits / 8;
        var sampleCount = dataSize / containerBytes;
        var output = new byte[sampleCount * validBytes];

        for (int i = 0; i < sampleCount; i++)
        {
            var src = dataStart + i * containerBytes;
            var dst = i * validBytes;
            // Little-endian: the valid sample occupies the low bytes; the upper bytes are padding /
            // sign extension and are discarded.
            for (int b = 0; b < validBytes; b++)
            {
                output[dst + b] = buffer[src + b];
            }
        }

        return output;
    }

    /// <summary>
    /// Returns default WAV metadata for fallback scenarios
    /// </summary>
    private WavMetadata GetDefaultWavMetadata()
    {
        return new WavMetadata
        {
            Duration = 180.0,
            Bitrate = 1411,
            SampleRate = 44100,
            Channels = 2,
            BitsPerSample = 16,
            BlockAlign = 4,
            DataSize = 0
        };
    }

    /// <summary>
    /// Finds a chunk in the WAV file buffer with proper alignment handling
    /// </summary>
    private static int FindChunk(byte[] buffer, string chunkId)
    {
        var chunkBytes = System.Text.Encoding.ASCII.GetBytes(chunkId);
        int offset = 12; // Start after RIFF header
        
        while (offset <= buffer.Length - 8)
        {
            // Check for chunk signature match
            bool match = true;
            for (int i = 0; i < 4; i++)
            {
                if (buffer[offset + i] != chunkBytes[i])
                {
                    match = false;
                    break;
                }
            }
            
            if (match)
            {
                return offset;
            }
            
            // Move to next chunk with proper alignment
            if (offset + 4 < buffer.Length)
            {
                var chunkSize = BitConverter.ToUInt32(buffer, offset + 4);
                offset += 8 + (int)((chunkSize + 1) & ~1U); // Ensure even alignment
            }
            else
            {
                break;
            }
        }
        
        return -1;
    }

    /// <summary>
    /// WAV file metadata with complete audio information
    /// </summary>
    private class WavMetadata
    {
        public double Duration { get; set; }
        public int Bitrate { get; set; }
        public int SampleRate { get; set; }
        public int Channels { get; set; }

        /// <summary>The valid sample depth — for EXTENSIBLE, wValidBitsPerSample.</summary>
        public int BitsPerSample { get; set; }

        /// <summary>
        /// The container sample width for a padded EXTENSIBLE WAV whose valid depth is narrower
        /// (e.g. 32 for a 24-in-32 file). Zero when the container matches the valid depth.
        /// </summary>
        public int ContainerBitsPerSample { get; set; }

        public int BlockAlign { get; set; }
        public int DataSize { get; set; }
        public int DataChunkPos { get; set; }
        public bool IsExtensible { get; set; }

        /// <summary>True when the SubFormat is IEEE float (converted to 24-bit PCM on normalization).</summary>
        public bool IsFloat { get; set; }

        /// <summary>True when valid samples are stored in a wider container that must be re-packed.</summary>
        public bool IsPaddedContainer => ContainerBitsPerSample != 0 && ContainerBitsPerSample != BitsPerSample;
    }
    
    /// <summary>
    /// Result of WAV structure validation
    /// </summary>
    private class WavValidationResult
    {
        public bool IsValid { get; set; }
        public string ErrorMessage { get; set; } = string.Empty;
        public int FmtChunkPos { get; set; }
        public int DataChunkPos { get; set; }
        public bool IsExtensible { get; set; }

        /// <summary>True when the EXTENSIBLE SubFormat is IEEE float rather than PCM.</summary>
        public bool IsFloat { get; set; }
    }
}

/// <summary>
/// The raw PCM sample region of a WAV plus the format parameters needed to interpret it.
/// <see cref="Pcm"/> is a view over the decoded buffer — the data chunk only, header excluded.
/// </summary>
/// <param name="Pcm">The PCM sample bytes (interleaved by channel, little-endian).</param>
/// <param name="Channels">Number of interleaved channels.</param>
/// <param name="SampleRate">Samples per second.</param>
/// <param name="BitsPerSample">Bit depth per sample (8, 16, 24, or 32).</param>
public readonly record struct PcmData(
    ReadOnlyMemory<byte> Pcm,
    int Channels,
    int SampleRate,
    int BitsPerSample);

/// <summary>
/// Where a WAV's PCM data region lives and how to decode it, without the bytes themselves — the
/// streaming counterpart of <see cref="PcmData"/>. The caller seeks to <see cref="DataStart"/> and
/// streams exactly <see cref="DataLength"/> bytes through a loudness accumulator.
/// </summary>
/// <param name="DataStart">Absolute byte offset of the first PCM sample (past the data chunk header).</param>
/// <param name="DataLength">PCM region length in bytes, clamped to what the backing file actually holds.</param>
/// <param name="Channels">Number of interleaved channels.</param>
/// <param name="SampleRate">Samples per second.</param>
/// <param name="BitsPerSample">Bit depth per sample (8, 16, 24, or 32).</param>
public readonly record struct WavPcmStreamInfo(
    long DataStart,
    long DataLength,
    int Channels,
    int SampleRate,
    int BitsPerSample);