vaultik/internal/database/files.go

package database

import (
	"context"
	"database/sql"
	"fmt"
	"time"

	"git.eeqj.de/sneak/vaultik/internal/log"
	"git.eeqj.de/sneak/vaultik/internal/types"
)

type FileRepository struct {
	db *DB
}

func NewFileRepository(db *DB) *FileRepository {
	return &FileRepository{db: db}
}

func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) error {
	// Generate UUID if not provided
	if file.ID.IsZero() {
		file.ID = types.NewFileID()
	}

	query := `
		INSERT INTO files (id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target)
		VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
		ON CONFLICT(path) DO UPDATE SET
			source_path = excluded.source_path,
			mtime = excluded.mtime,
			ctime = excluded.ctime,
			size = excluded.size,
			mode = excluded.mode,
			uid = excluded.uid,
			gid = excluded.gid,
			link_target = excluded.link_target
		RETURNING id
	`

	var idStr string
	var err error
	if tx != nil {
		LogSQL("Execute", query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String())
		err = tx.QueryRowContext(ctx, query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String()).Scan(&idStr)
	} else {
		err = r.db.QueryRowWithLog(ctx, query, file.ID.String(), file.Path.String(), file.SourcePath.String(), file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget.String()).Scan(&idStr)
	}

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

	// Parse the returned ID
	file.ID, err = types.ParseFileID(idStr)
	if err != nil {
		return fmt.Errorf("parsing file ID: %w", err)
	}

	return nil
}

func (r *FileRepository) GetByPath(ctx context.Context, path string) (*File, error) {
	query := `
		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
		FROM files
		WHERE path = ?
	`

	file, err := r.scanFile(r.db.conn.QueryRowContext(ctx, query, path))
	if err == sql.ErrNoRows {
		return nil, nil
	}
	if err != nil {
		return nil, fmt.Errorf("querying file: %w", err)
	}

	return file, nil
}

// GetByID retrieves a file by its UUID
func (r *FileRepository) GetByID(ctx context.Context, id types.FileID) (*File, error) {
	query := `
		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
		FROM files
		WHERE id = ?
	`

	file, err := r.scanFile(r.db.conn.QueryRowContext(ctx, query, id.String()))
	if err == sql.ErrNoRows {
		return nil, nil
	}
	if err != nil {
		return nil, fmt.Errorf("querying file: %w", err)
	}

	return file, nil
}

func (r *FileRepository) GetByPathTx(ctx context.Context, tx *sql.Tx, path string) (*File, error) {
	query := `
		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
		FROM files
		WHERE path = ?
	`

	LogSQL("GetByPathTx QueryRowContext", query, path)
	file, err := r.scanFile(tx.QueryRowContext(ctx, query, path))
	LogSQL("GetByPathTx Scan complete", query, path)

	if err == sql.ErrNoRows {
		return nil, nil
	}
	if err != nil {
		return nil, fmt.Errorf("querying file: %w", err)
	}

	return file, nil
}

// scanFile is a helper that scans a single file row
func (r *FileRepository) scanFile(row *sql.Row) (*File, error) {
	var file File
	var idStr, pathStr, sourcePathStr string
	var mtimeUnix, ctimeUnix int64
	var linkTarget sql.NullString

	err := row.Scan(
		&idStr,
		&pathStr,
		&sourcePathStr,
		&mtimeUnix,
		&ctimeUnix,
		&file.Size,
		&file.Mode,
		&file.UID,
		&file.GID,
		&linkTarget,
	)
	if err != nil {
		return nil, err
	}

	file.ID, err = types.ParseFileID(idStr)
	if err != nil {
		return nil, fmt.Errorf("parsing file ID: %w", err)
	}
	file.Path = types.FilePath(pathStr)
	file.SourcePath = types.SourcePath(sourcePathStr)
	file.MTime = time.Unix(mtimeUnix, 0).UTC()
	file.CTime = time.Unix(ctimeUnix, 0).UTC()
	if linkTarget.Valid {
		file.LinkTarget = types.FilePath(linkTarget.String)
	}

	return &file, nil
}

// scanFileRows is a helper that scans a file row from rows iterator
func (r *FileRepository) scanFileRows(rows *sql.Rows) (*File, error) {
	var file File
	var idStr, pathStr, sourcePathStr string
	var mtimeUnix, ctimeUnix int64
	var linkTarget sql.NullString

	err := rows.Scan(
		&idStr,
		&pathStr,
		&sourcePathStr,
		&mtimeUnix,
		&ctimeUnix,
		&file.Size,
		&file.Mode,
		&file.UID,
		&file.GID,
		&linkTarget,
	)
	if err != nil {
		return nil, err
	}

	file.ID, err = types.ParseFileID(idStr)
	if err != nil {
		return nil, fmt.Errorf("parsing file ID: %w", err)
	}
	file.Path = types.FilePath(pathStr)
	file.SourcePath = types.SourcePath(sourcePathStr)
	file.MTime = time.Unix(mtimeUnix, 0).UTC()
	file.CTime = time.Unix(ctimeUnix, 0).UTC()
	if linkTarget.Valid {
		file.LinkTarget = types.FilePath(linkTarget.String)
	}

	return &file, nil
}

func (r *FileRepository) ListModifiedSince(ctx context.Context, since time.Time) ([]*File, error) {
	query := `
		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
		FROM files
		WHERE mtime >= ?
		ORDER BY path
	`

	rows, err := r.db.conn.QueryContext(ctx, query, since.Unix())
	if err != nil {
		return nil, fmt.Errorf("querying files: %w", err)
	}
	defer CloseRows(rows)

	var files []*File
	for rows.Next() {
		file, err := r.scanFileRows(rows)
		if err != nil {
			return nil, fmt.Errorf("scanning file: %w", err)
		}
		files = append(files, file)
	}

	return files, rows.Err()
}

func (r *FileRepository) Delete(ctx context.Context, tx *sql.Tx, path string) error {
	query := `DELETE FROM files WHERE path = ?`

	var err error
	if tx != nil {
		_, err = tx.ExecContext(ctx, query, path)
	} else {
		_, err = r.db.ExecWithLog(ctx, query, path)
	}

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

	return nil
}

// DeleteByID deletes a file by its UUID
func (r *FileRepository) DeleteByID(ctx context.Context, tx *sql.Tx, id types.FileID) error {
	query := `DELETE FROM files WHERE id = ?`

	var err error
	if tx != nil {
		_, err = tx.ExecContext(ctx, query, id.String())
	} else {
		_, err = r.db.ExecWithLog(ctx, query, id.String())
	}

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

	return nil
}

func (r *FileRepository) ListByPrefix(ctx context.Context, prefix string) ([]*File, error) {
	query := `
		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
		FROM files
		WHERE path LIKE ? || '%'
		ORDER BY path
	`

	rows, err := r.db.conn.QueryContext(ctx, query, prefix)
	if err != nil {
		return nil, fmt.Errorf("querying files: %w", err)
	}
	defer CloseRows(rows)

	var files []*File
	for rows.Next() {
		file, err := r.scanFileRows(rows)
		if err != nil {
			return nil, fmt.Errorf("scanning file: %w", err)
		}
		files = append(files, file)
	}

	return files, rows.Err()
}

// ListAll returns all files in the database
func (r *FileRepository) ListAll(ctx context.Context) ([]*File, error) {
	query := `
		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
		FROM files
		ORDER BY path
	`

	rows, err := r.db.conn.QueryContext(ctx, query)
	if err != nil {
		return nil, fmt.Errorf("querying files: %w", err)
	}
	defer CloseRows(rows)

	var files []*File
	for rows.Next() {
		file, err := r.scanFileRows(rows)
		if err != nil {
			return nil, fmt.Errorf("scanning file: %w", err)
		}
		files = append(files, file)
	}

	return files, rows.Err()
}

// CreateBatch inserts or updates multiple files in a single statement for efficiency.
// File IDs must be pre-generated before calling this method.
func (r *FileRepository) CreateBatch(ctx context.Context, tx *sql.Tx, files []*File) error {
	if len(files) == 0 {
		return nil
	}

	// Each File has 10 values, so batch at 100 to be safe with SQLite's variable limit
	const batchSize = 100

	for i := 0; i < len(files); i += batchSize {
		end := i + batchSize
		if end > len(files) {
			end = len(files)
		}
		batch := files[i:end]

		query := `INSERT INTO files (id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target) VALUES `
		args := make([]interface{}, 0, len(batch)*10)
		for j, f := range batch {
			if j > 0 {
				query += ", "
			}
			query += "(?, ?, ?, ?, ?, ?, ?, ?, ?, ?)"
			args = append(args, f.ID.String(), f.Path.String(), f.SourcePath.String(), f.MTime.Unix(), f.CTime.Unix(), f.Size, f.Mode, f.UID, f.GID, f.LinkTarget.String())
		}
		query += ` ON CONFLICT(path) DO UPDATE SET
			source_path = excluded.source_path,
			mtime = excluded.mtime,
			ctime = excluded.ctime,
			size = excluded.size,
			mode = excluded.mode,
			uid = excluded.uid,
			gid = excluded.gid,
			link_target = excluded.link_target`

		var err error
		if tx != nil {
			_, err = tx.ExecContext(ctx, query, args...)
		} else {
			_, err = r.db.ExecWithLog(ctx, query, args...)
		}
		if err != nil {
			return fmt.Errorf("batch inserting files: %w", err)
		}
	}

	return nil
}

// DeleteOrphaned deletes files that are not referenced by any snapshot
func (r *FileRepository) DeleteOrphaned(ctx context.Context) error {
	query := `
		DELETE FROM files
		WHERE NOT EXISTS (
			SELECT 1 FROM snapshot_files
			WHERE snapshot_files.file_id = files.id
		)
	`

	result, err := r.db.ExecWithLog(ctx, query)
	if err != nil {
		return fmt.Errorf("deleting orphaned files: %w", err)
	}

	rowsAffected, _ := result.RowsAffected()
	if rowsAffected > 0 {
		log.Debug("Deleted orphaned files", "count", rowsAffected)
	}

	return nil
}