DeutschLernen/GermanApp/Infrastructure/Services/TtsService.cs

using GermanApp.Domain.Interfaces;
using GermanApp.Infrastructure.Configuration;
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Options;
using System.Diagnostics;
using System.Text;
using System.Text.Json;

namespace GermanApp.Infrastructure.Services;

/// <summary>
/// Infrastructure service for Coqui TTS text-to-speech.
/// Uses Python process to call Coqui TTS library.
/// This is part of the Infrastructure layer.
/// </summary>
public class TtsService : ITtsService
{
    private readonly CoquiConfig _config;
    private readonly ILogger<TtsService> _logger;

    public TtsService(
        IOptions<CoquiConfig> config,
        ILogger<TtsService> logger)
    {
        _config = config.Value;
        _logger = logger;
        
        // Skip validation during EF migrations
        bool isEfDesignTime = Environment.GetEnvironmentVariable("DOTNET_RUNNING_IN_EF") == "true";
        if (!isEfDesignTime)
        {
            ValidateConfiguration();
            // Ensure audio storage directory exists
            Directory.CreateDirectory(_config.AudioStoragePath);
        }
    }

    /// <summary>
    /// Validates TTS configuration on startup.
    /// </summary>
    /// <exception cref="InvalidOperationException">Thrown when configuration is invalid</exception>
    private void ValidateConfiguration()
    {
        if (string.IsNullOrWhiteSpace(_config.PythonPath))
        {
            _logger.LogError("Coqui PythonPath is not configured");
            throw new InvalidOperationException(
                "Coqui PythonPath is not configured. Please set Coqui:PythonPath in appsettings.json");
        }

        if (string.IsNullOrWhiteSpace(_config.ModelName))
        {
            _logger.LogError("Coqui ModelName is not configured");
            throw new InvalidOperationException(
                "Coqui ModelName is not configured. Please set Coqui:ModelName in appsettings.json. " +
                "Example: tts_models/de/deu/fairseq/vits");
        }

        if (string.IsNullOrWhiteSpace(_config.AudioStoragePath))
        {
            _logger.LogError("Coqui AudioStoragePath is not configured");
            throw new InvalidOperationException(
                "Coqui AudioStoragePath is not configured. Please set Coqui:AudioStoragePath in appsettings.json");
        }

        if (_config.MaxTextLength <= 0)
        {
            _logger.LogError("Coqui MaxTextLength must be positive");
            throw new InvalidOperationException(
                "Coqui MaxTextLength must be greater than 0");
        }

        if (_config.TimeoutSeconds <= 0)
        {
            _logger.LogError("Coqui TimeoutSeconds must be positive");
            throw new InvalidOperationException(
                "Coqui TimeoutSeconds must be greater than 0");
        }

        _logger.LogInformation("Coqui TTS configuration validated: Model={ModelName}, Storage={AudioStoragePath}",
            _config.ModelName, _config.AudioStoragePath);
    }

    /// <summary>
    /// Generates audio from text.
    /// </summary>
    public virtual async Task<byte[]> GenerateAudioAsync(
        string text,
        string? speaker = null,
        string language = "de",
        CancellationToken cancellationToken = default)
    {
        if (string.IsNullOrWhiteSpace(text))
            throw new ArgumentException("Text cannot be empty", nameof(text));

        // Split long text into chunks
        if (text.Length > _config.MaxTextLength)
        {
            var chunks = SplitText(text, _config.MaxTextLength);
            var audioParts = new List<byte[]>();
            
            foreach (var chunk in chunks)
            {
                var audio = await GenerateAudioForChunkAsync(chunk, speaker, language, cancellationToken);
                audioParts.Add(audio);
            }
            
            // Combine audio bytes
            return CombineAudioBytes(audioParts);
        }
        
        return await GenerateAudioForChunkAsync(text, speaker, language, cancellationToken);
    }

    /// <summary>
    /// Generates audio for a single text chunk.
    /// </summary>
    private async Task<byte[]> GenerateAudioForChunkAsync(
        string text,
        string? speaker,
        string language,
        CancellationToken cancellationToken)
    {
        var tempFile = Path.GetTempFileName() + "." + _config.OutputFormat;
        try
        {
            await GenerateAudioToFileInternalAsync(text, tempFile, speaker, language, cancellationToken);
            return await File.ReadAllBytesAsync(tempFile, cancellationToken);
        }
        finally
        {
            try { File.Delete(tempFile); }
            catch (Exception ex) { _logger.LogError(ex, "Failed to delete temp file: {File}", tempFile); }
        }
    }

    /// <summary>
    /// Generates audio and saves to a file.
    /// </summary>
    public virtual async Task<string> GenerateAudioToFileAsync(
        string text,
        string outputPath,
        string? speaker = null,
        string language = "de",
        CancellationToken cancellationToken = default)
    {
        if (string.IsNullOrWhiteSpace(text))
            throw new ArgumentException("Text cannot be empty", nameof(text));

        // Ensure output directory exists
        var directory = Path.GetDirectoryName(outputPath);
        if (!string.IsNullOrEmpty(directory))
            Directory.CreateDirectory(directory);

        await GenerateAudioToFileInternalAsync(text, outputPath, speaker, language, cancellationToken);
        
        return outputPath;
    }

    /// <summary>
    /// Internal method to generate audio to a specific file path.
    /// </summary>
    private async Task GenerateAudioToFileInternalAsync(
        string text,
        string outputPath,
        string? speaker,
        string language,
        CancellationToken cancellationToken)
    {
        var script = BuildTtsScript(text, outputPath, speaker, language);
        var tempScript = Path.GetTempFileName() + ".py";
        
        try
        {
            await File.WriteAllTextAsync(tempScript, script, cancellationToken);
            
            var result = await ExecutePythonProcessAsync(tempScript, cancellationToken);
            
            if (result.ExitCode != 0)
            {
                _logger.LogError("TTS generation failed. stderr: {Error}", result.StandardError);
                throw new InvalidOperationException(
                    "TTS generation failed: " + result.StandardError);
            }
            
            // Verify output file exists
            if (!File.Exists(outputPath))
            {
                throw new FileNotFoundException(
                    "TTS output file not created", outputPath);
            }
        }
        finally
        {
            try { File.Delete(tempScript); }
            catch (Exception ex) { _logger.LogError(ex, "Failed to delete temp script: {File}", tempScript); }
        }
    }

    /// <summary>
    /// Generates audio as a stream.
    /// </summary>
    public virtual async Task<System.IO.Stream> GenerateAudioStreamAsync(
        string text,
        string? speaker = null,
        string language = "de",
        CancellationToken cancellationToken = default)
    {
        // For streaming, we generate to a temp file and return a FileStream
        var tempFile = Path.GetTempFileName() + "." + _config.OutputFormat;
        
        try
        {
            await GenerateAudioToFileInternalAsync(text, tempFile, speaker, language, cancellationToken);
            return new FileStream(tempFile, FileMode.Open, FileAccess.Read, FileShare.Read, 4096, true);
        }
        catch
        {
            // Clean up on error
            try { File.Delete(tempFile); }
            catch { }
            throw;
        }
    }

    /// <summary>
    /// Builds the Python script for TTS generation.
    /// </summary>
    private string BuildTtsScript(string text, string outputPath, string? speaker, string language)
    {
        var script = new StringBuilder();
        script.AppendLine("import sys");
        script.AppendLine("import json");
        script.AppendLine();
        
        // Handle import errors
        script.AppendLine("try:");
        script.AppendLine("    from TTS.api import TTS");
        script.AppendLine("except ImportError as e:");
        script.AppendLine("    print(json.dumps({'error': 'Coqui TTS not installed: ' + str(e)}))");
        script.AppendLine("    sys.exit(1)");
        script.AppendLine();
        
        // Load TTS model
        script.AppendLine($"model_name = '{_config.ModelName}'");
        script.AppendLine("try:");
        script.AppendLine("    tts = TTS(model_name=model_name)");
        script.AppendLine("except Exception as e:");
        script.AppendLine("    print(json.dumps({'error': 'Failed to load TTS model: ' + str(e)}))");
        script.AppendLine("    sys.exit(1)");
        script.AppendLine();
        
        // Configure TTS
        if (!string.IsNullOrEmpty(speaker))
        {
            script.AppendLine($"tts.speaker = '{speaker}'");
        }
        script.AppendLine($"tts.language = '{language}'");
        script.AppendLine();
        
        // Generate and save audio
        script.AppendLine($"text = '''{text.Replace("'''", "\\'''")}'''");
        script.AppendLine($"output_path = '{outputPath.Replace("\\", "\\\\")}'");
        script.AppendLine("tts.tts_to_file(text=text, file_path=output_path)");
        script.AppendLine("print('success')");
        
        return script.ToString();
    }

    /// <summary>
    /// Result of Python process execution.
    /// </summary>
    private class ProcessResult
    {
        public string StandardOutput { get; set; } = string.Empty;
        public string StandardError { get; set; } = string.Empty;
        public int ExitCode { get; set; }
    }

    /// <summary>
    /// Executes a Python process and returns the result.
    /// </summary>
    private async Task<ProcessResult> ExecutePythonProcessAsync(
        string scriptPath,
        CancellationToken cancellationToken)
    {
        var processInfo = new ProcessStartInfo
        {
            FileName = _config.PythonPath,
            Arguments = scriptPath,
            RedirectStandardOutput = true,
            RedirectStandardError = true,
            UseShellExecute = false,
            CreateNoWindow = true,
            StandardOutputEncoding = Encoding.UTF8,
            StandardErrorEncoding = Encoding.UTF8
        };

        using var process = new Process { StartInfo = processInfo };
        
        // Use a timeout for the process
        var timeoutTask = Task.Delay(_config.TimeoutSeconds * 1000, cancellationToken);
        
        process.Start();
        
        var outputTask = process.StandardOutput.ReadToEndAsync();
        var errorTask = process.StandardError.ReadToEndAsync();
        var exitTask = process.WaitForExitAsync(cancellationToken);
        
        // Wait for process to complete or timeout
        var completedTask = await Task.WhenAny(exitTask, timeoutTask);
        
        if (completedTask == timeoutTask)
        {
            // Kill the process if it times out
            try { process.Kill(); }
            catch { }
            
            _logger.LogError("TTS process timed out after {Seconds} seconds", _config.TimeoutSeconds);
            throw new TimeoutException(
                $"TTS generation timed out after {_config.TimeoutSeconds} seconds");
        }
        
        var output = await outputTask;
        var error = await errorTask;
        
        return new ProcessResult
        {
            StandardOutput = output,
            StandardError = error,
            ExitCode = process.ExitCode
        };
    }

    /// <summary>
    /// Splits text into chunks of maximum length.
    /// </summary>
    private IReadOnlyList<string> SplitText(string text, int maxLength)
    {
        var chunks = new List<string>();
        var currentChunk = new StringBuilder();
        
        foreach (var word in text.Split(new[] { ' ', '\n', '\r', '\t' }, StringSplitOptions.RemoveEmptyEntries))
        {
            if (currentChunk.Length + word.Length + 1 <= maxLength)
            {
                if (currentChunk.Length > 0)
                    currentChunk.Append(' ');
                currentChunk.Append(word);
            }
            else
            {
                chunks.Add(currentChunk.ToString());
                currentChunk.Clear();
                currentChunk.Append(word);
            }
        }
        
        if (currentChunk.Length > 0)
            chunks.Add(currentChunk.ToString());
        
        return chunks;
    }

    /// <summary>
    /// Combines multiple audio byte arrays into a single array.
    /// Note: This is a simple concatenation. For proper audio merging,
    /// you would need to use an audio library to handle the WAV header correctly.
    /// </summary>
    private byte[] CombineAudioBytes(IReadOnlyList<byte[]> audioParts)
    {
        if (audioParts.Count == 1)
            return audioParts[0];
        
        // For WAV files, we need to handle the header properly
        // This is a simplified version that assumes all parts are valid WAV files
        // In production, you would want to use NAudio or similar to properly merge WAV files
        
        var totalLength = audioParts.Sum(p => p.Length);
        var combined = new byte[totalLength];
        var offset = 0;
        
        foreach (var part in audioParts)
        {
            Buffer.BlockCopy(part, 0, combined, offset, part.Length);
            offset += part.Length;
        }
        
        return combined;
    }

    /// <summary>
    /// Tests the Coqui TTS model and configuration.
    /// </summary>
    public virtual async Task<bool> TestModelAsync(CancellationToken cancellationToken = default)
    {
        try
        {
            // Test with a simple phrase
            var testText = "Hallo, das ist ein Test.";
            var testFile = Path.Combine(_config.AudioStoragePath, "test." + _config.OutputFormat);
            
            await GenerateAudioToFileAsync(testText, testFile, null, "de", cancellationToken);
            
            // Verify file was created
            if (File.Exists(testFile))
            {
                // Clean up test file
                File.Delete(testFile);
                return true;
            }
            
            return false;
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "TTS model test failed");
            return false;
        }
    }

    /// <summary>
    /// Gets the current TTS model information.
    /// </summary>
    public virtual Task<(string ModelName, string? ModelPath)> GetModelInfoAsync()
    {
        return Task.FromResult<(string ModelName, string? ModelPath)>((_config.ModelName, null));
    }

    /// <summary>
    /// Gets list of available voices/speakers for the current model.
    /// </summary>
    public virtual Task<IReadOnlyList<string>> GetAvailableSpeakersAsync(CancellationToken cancellationToken = default)
    {
        // Coqui TTS doesn't always have multiple speakers for all models
        // This would need to query the model or use a predefined list
        // For now, return a default list for German models
        var defaultSpeakers = new List<string> { "default" };
        return Task.FromResult<IReadOnlyList<string>>(defaultSpeakers);
    }

    /// <summary>
    /// Cleans up old audio files from storage.
    /// </summary>
    public virtual async Task<int> CleanupOldFilesAsync(
        TimeSpan olderThan,
        CancellationToken cancellationToken = default)
    {
        var cutoff = DateTime.UtcNow - olderThan;
        var deletedCount = 0;
        
        if (Directory.Exists(_config.AudioStoragePath))
        {
            foreach (var file in Directory.GetFiles(_config.AudioStoragePath, "*", SearchOption.AllDirectories))
            {
                try
                {
                    var fileInfo = new FileInfo(file);
                    if (fileInfo.LastWriteTimeUtc < cutoff)
                    {
                        File.Delete(file);
                        deletedCount++;
                        _logger.LogInformation("Deleted old audio file: {File}", file);
                    }
                }
                catch (Exception ex)
                {
                    _logger.LogError(ex, "Failed to delete audio file: {File}", file);
                }
                
                // Yield to avoid blocking for long periods
                await Task.Yield();
            }
        }
        
        return deletedCount;
    }
}