//go:build linux

package engine

import (
	"fmt"
	"time"
	"voicesnap/internal/logger"
	"voicesnap/internal/model"

	_ "github.com/k2-fsa/sherpa-onnx-go-linux"
	sherpa "github.com/k2-fsa/sherpa-onnx-go/sherpa_onnx"
)

type sherpaEngine struct {
	recognizer *sherpa.OfflineRecognizer
	provider   string
	hwInfo     string
}

func newPlatformEngine(resolved model.ResolvedModel) (Engine, error) {
	// Linux: CPU only
	config := sherpa.OfflineRecognizerConfig{}
	config.FeatConfig.SampleRate = 16000
	config.FeatConfig.FeatureDim = 80
	config.ModelConfig.SenseVoice.Model = resolved.Files["model"]
	config.ModelConfig.SenseVoice.Language = resolved.Profile.LanguageParam
	config.ModelConfig.SenseVoice.UseInverseTextNormalization = 1
	config.ModelConfig.Tokens = resolved.Files["tokens"]
	config.ModelConfig.NumThreads = resolved.Profile.NumThreads
	config.ModelConfig.Provider = "cpu"
	config.DecodingMethod = "greedy_search"

	recognizer := sherpa.NewOfflineRecognizer(&config)
	if recognizer != nil {
		info := "SenseVoice · CPU"
		logger.Info("Engine initialized: %s", info)
		return &sherpaEngine{
			recognizer: recognizer,
			provider:   "cpu",
			hwInfo:     info,
		}, nil
	}

	return nil, fmt.Errorf("failed to initialize sherpa-onnx on Linux")
}

func (e *sherpaEngine) Recognize(samples []float32) (string, error) {
	totalStart := time.Now()
	streamStart := time.Now()
	stream := sherpa.NewOfflineStream(e.recognizer)
	streamMS := durationMS(time.Since(streamStart))
	defer sherpa.DeleteOfflineStream(stream)

	acceptStart := time.Now()
	stream.AcceptWaveform(16000, samples)
	acceptMS := durationMS(time.Since(acceptStart))

	decodeStart := time.Now()
	e.recognizer.Decode(stream)
	decodeMS := durationMS(time.Since(decodeStart))
	resultStart := time.Now()
	result := stream.GetResult()
	resultMS := durationMS(time.Since(resultStart))
	logger.Info(
		"PERF engine_recognize_detail backend=%q provider=%q engine=%q samples=%d audio_ms=%d create_stream_ms=%d accept_ms=%d decode_ms=%d result_ms=%d total_ms=%d",
		model.BackendSenseVoice,
		e.provider,
		e.hwInfo,
		len(samples),
		audioDurationMS(samples),
		streamMS,
		acceptMS,
		decodeMS,
		resultMS,
		durationMS(time.Since(totalStart)),
	)

	return result.Text, nil
}

func (e *sherpaEngine) HardwareInfo() string {
	return e.hwInfo
}

func (e *sherpaEngine) Provider() string {
	return e.provider
}

func (e *sherpaEngine) ReleaseTailCaptureDelay() time.Duration {
	return senseVoiceReleaseTailDelay
}

func (e *sherpaEngine) Close() {
	if e.recognizer != nil {
		sherpa.DeleteOfflineRecognizer(e.recognizer)
		e.recognizer = nil
	}
}