vaultik/internal/backup/scanner.go

package backup

import (
	"context"
	"crypto/sha256"
	"database/sql"
	"encoding/hex"
	"fmt"
	"io"
	"os"
	"time"

	"git.eeqj.de/sneak/vaultik/internal/database"
	"github.com/spf13/afero"
)

// Scanner scans directories and populates the database with file and chunk information
type Scanner struct {
	fs        afero.Fs
	chunkSize int
	repos     *database.Repositories
}

// ScannerConfig contains configuration for the scanner
type ScannerConfig struct {
	FS           afero.Fs
	ChunkSize    int
	Repositories *database.Repositories
}

// ScanResult contains the results of a scan operation
type ScanResult struct {
	FilesScanned int
	BytesScanned int64
	StartTime    time.Time
	EndTime      time.Time
}

// NewScanner creates a new scanner instance
func NewScanner(cfg ScannerConfig) *Scanner {
	return &Scanner{
		fs:        cfg.FS,
		chunkSize: cfg.ChunkSize,
		repos:     cfg.Repositories,
	}
}

// Scan scans a directory and populates the database
func (s *Scanner) Scan(ctx context.Context, path string) (*ScanResult, error) {
	result := &ScanResult{
		StartTime: time.Now(),
	}

	// Start a transaction
	err := s.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
		return s.scanDirectory(ctx, tx, path, result)
	})

	if err != nil {
		return nil, fmt.Errorf("scan failed: %w", err)
	}

	result.EndTime = time.Now()
	return result, nil
}

func (s *Scanner) scanDirectory(ctx context.Context, tx *sql.Tx, path string, result *ScanResult) error {
	return afero.Walk(s.fs, path, func(path string, info os.FileInfo, err error) error {
		if err != nil {
			return err
		}

		// Check context cancellation
		select {
		case <-ctx.Done():
			return ctx.Err()
		default:
		}

		// Skip directories
		if info.IsDir() {
			return nil
		}

		// Process the file
		if err := s.processFile(ctx, tx, path, info, result); err != nil {
			return fmt.Errorf("failed to process %s: %w", path, err)
		}

		return nil
	})
}

func (s *Scanner) processFile(ctx context.Context, tx *sql.Tx, path string, info os.FileInfo, result *ScanResult) error {
	// Get file stats
	stat, ok := info.Sys().(interface {
		Uid() uint32
		Gid() uint32
	})

	var uid, gid uint32
	if ok {
		uid = stat.Uid()
		gid = stat.Gid()
	}

	// Check if it's a symlink
	var linkTarget string
	if info.Mode()&os.ModeSymlink != 0 {
		// Read the symlink target
		if linker, ok := s.fs.(afero.LinkReader); ok {
			linkTarget, _ = linker.ReadlinkIfPossible(path)
		}
	}

	// Create file record
	file := &database.File{
		Path:       path,
		MTime:      info.ModTime(),
		CTime:      info.ModTime(), // afero doesn't provide ctime
		Size:       info.Size(),
		Mode:       uint32(info.Mode()),
		UID:        uid,
		GID:        gid,
		LinkTarget: linkTarget,
	}

	// Insert file
	if err := s.repos.Files.Create(ctx, tx, file); err != nil {
		return err
	}

	result.FilesScanned++
	result.BytesScanned += info.Size()

	// Process chunks only for regular files
	if info.Mode().IsRegular() && info.Size() > 0 {
		if err := s.processFileChunks(ctx, tx, path, result); err != nil {
			return err
		}
	}

	return nil
}

func (s *Scanner) processFileChunks(ctx context.Context, tx *sql.Tx, path string, result *ScanResult) error {
	file, err := s.fs.Open(path)
	if err != nil {
		return err
	}
	defer func() {
		if err := file.Close(); err != nil {
			database.Fatal("failed to close file %s: %v", path, err)
		}
	}()

	sequence := 0
	buffer := make([]byte, s.chunkSize)

	for {
		n, err := io.ReadFull(file, buffer)
		if err != nil && err != io.EOF && err != io.ErrUnexpectedEOF {
			return err
		}

		if n == 0 {
			break
		}

		// Calculate chunk hash
		h := sha256.New()
		h.Write(buffer[:n])
		hash := hex.EncodeToString(h.Sum(nil))

		// Create chunk if it doesn't exist
		chunk := &database.Chunk{
			ChunkHash: hash,
			SHA256:    hash, // Using same hash for now
			Size:      int64(n),
		}

		// Try to insert chunk (ignore duplicate errors)
		_ = s.repos.Chunks.Create(ctx, tx, chunk)

		// Create file-chunk mapping
		fileChunk := &database.FileChunk{
			Path:      path,
			ChunkHash: hash,
			Idx:       sequence,
		}

		if err := s.repos.FileChunks.Create(ctx, tx, fileChunk); err != nil {
			return err
		}

		// Create chunk-file mapping
		chunkFile := &database.ChunkFile{
			ChunkHash:  hash,
			FilePath:   path,
			FileOffset: int64(sequence * s.chunkSize),
			Length:     int64(n),
		}

		if err := s.repos.ChunkFiles.Create(ctx, tx, chunkFile); err != nil {
			return err
		}

		sequence++

		if err == io.EOF || err == io.ErrUnexpectedEOF {
			break
		}
	}

	return nil
}