package benchmarks

import (
	"os"
	"path/filepath"
	"testing"

	"github.com/jfraeys/fetch_ml/internal/worker"
)

// createSmallDataset creates a temporary small dataset for benchmarking
func createSmallDataset(b *testing.B) string {
	tmpDir := b.TempDir()
	// Create 10 small files (100KB each) to emphasize context overhead
	data := make([]byte, 100*1024)
	for i := range data {
		data[i] = byte(i % 256)
	}
	for i := range 10 {
		path := filepath.Join(tmpDir, "data", string(rune('a'+i%26)), "chunk.bin")
		if err := os.MkdirAll(filepath.Dir(path), 0750); err != nil {
			b.Fatal(err)
		}
		if err := os.WriteFile(path, data, 0640); err != nil {
			b.Fatal(err)
		}
	}
	return tmpDir
}

// BenchmarkContextReuse measures overhead of repeated hash operations
// This verifies the 5-20ms savings from context reuse in native_bridge_libs.go
func BenchmarkContextReuse(b *testing.B) {
	testDir := createSmallDataset(b)

	b.ResetTimer()
	for i := 0; i < b.N; i++ {
		_, err := worker.DirOverallSHA256Hex(testDir)
		if err != nil {
			b.Fatal(err)
		}
	}
}

// BenchmarkSequentialHashes simulates TUI scrolling through datasets
// With context reuse: ~8ms per hash
// Without context reuse: ~17ms per hash (9ms overhead)
func BenchmarkSequentialHashes(b *testing.B) {
	testDir := createSmallDataset(b)

	b.ReportAllocs()

	for b.Loop() {
		// Simulate viewing 10 datasets (like TUI scrolling)
		for range 10 {
			_, err := worker.DirOverallSHA256Hex(testDir)
			if err != nil {
				b.Fatal(err)
			}
		}
	}
}