Add custom types, version command, and restore --verify flag

- Add internal/types package with type-safe wrappers for IDs, hashes, paths, and credentials (FileID, BlobID, ChunkHash, etc.) - Implement driver.Valuer and sql.Scanner for UUID-based types - Add `vaultik version` command showing version, commit, go version - Add `--verify` flag to restore command that checksums all restored files against expected chunk hashes with progress bar - Remove fetch.go (dead code, functionality in restore) - Clean up TODO.md, remove completed items - Update all database and snapshot code to use new custom types
2026-01-14 17:11:52 -08:00
parent 2afd54d693
commit 417b25a5f5
53 changed files with 2330 additions and 1581 deletions
--- a/internal/database/files.go
+++ b/internal/database/files.go
@@ -7,7 +7,7 @@ import (
 	"time"

 	"git.eeqj.de/sneak/vaultik/internal/log"
-	"github.com/google/uuid"
+	"git.eeqj.de/sneak/vaultik/internal/types"
 )

 type FileRepository struct {
@@ -20,14 +20,15 @@ func NewFileRepository(db *DB) *FileRepository {

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

 	query := `
-		INSERT INTO files (id, path, mtime, ctime, size, mode, uid, gid, link_target)
-		VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
+		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,
@@ -38,44 +39,36 @@ func (r *FileRepository) Create(ctx context.Context, tx *sql.Tx, file *File) err
 		RETURNING id
 	`

+	var idStr string
 	var err error
 	if tx != nil {
-		LogSQL("Execute", query, file.ID, file.Path, file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget)
-		err = tx.QueryRowContext(ctx, query, file.ID, file.Path, file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget).Scan(&file.ID)
+		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, file.Path, file.MTime.Unix(), file.CTime.Unix(), file.Size, file.Mode, file.UID, file.GID, file.LinkTarget).Scan(&file.ID)
+		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, mtime, ctime, size, mode, uid, gid, link_target
+		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
 		FROM files
 		WHERE path = ?
 	`

-	var file File
-	var mtimeUnix, ctimeUnix int64
-	var linkTarget sql.NullString
-
-	err := r.db.conn.QueryRowContext(ctx, query, path).Scan(
-		&file.ID,
-		&file.Path,
-		&mtimeUnix,
-		&ctimeUnix,
-		&file.Size,
-		&file.Mode,
-		&file.UID,
-		&file.GID,
-		&linkTarget,
-	)
-
+	file, err := r.scanFile(r.db.conn.QueryRowContext(ctx, query, path))
 	if err == sql.ErrNoRows {
 		return nil, nil
 	}
@@ -83,39 +76,18 @@ func (r *FileRepository) GetByPath(ctx context.Context, path string) (*File, err
 		return nil, fmt.Errorf("querying file: %w", err)
 	}

-	file.MTime = time.Unix(mtimeUnix, 0).UTC()
-	file.CTime = time.Unix(ctimeUnix, 0).UTC()
-	if linkTarget.Valid {
-		file.LinkTarget = linkTarget.String
-	}
-
-	return &file, nil
+	return file, nil
 }

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

-	var file File
-	var mtimeUnix, ctimeUnix int64
-	var linkTarget sql.NullString
-
-	err := r.db.conn.QueryRowContext(ctx, query, id).Scan(
-		&file.ID,
-		&file.Path,
-		&mtimeUnix,
-		&ctimeUnix,
-		&file.Size,
-		&file.Mode,
-		&file.UID,
-		&file.GID,
-		&linkTarget,
-	)
-
+	file, err := r.scanFile(r.db.conn.QueryRowContext(ctx, query, id.String()))
 	if err == sql.ErrNoRows {
 		return nil, nil
 	}
@@ -123,38 +95,18 @@ func (r *FileRepository) GetByID(ctx context.Context, id string) (*File, error)
 		return nil, fmt.Errorf("querying file: %w", err)
 	}

-	file.MTime = time.Unix(mtimeUnix, 0).UTC()
-	file.CTime = time.Unix(ctimeUnix, 0).UTC()
-	if linkTarget.Valid {
-		file.LinkTarget = linkTarget.String
-	}
-
-	return &file, nil
+	return file, nil
 }

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

-	var file File
-	var mtimeUnix, ctimeUnix int64
-	var linkTarget sql.NullString
-
 	LogSQL("GetByPathTx QueryRowContext", query, path)
-	err := tx.QueryRowContext(ctx, query, path).Scan(
-		&file.ID,
-		&file.Path,
-		&mtimeUnix,
-		&ctimeUnix,
-		&file.Size,
-		&file.Mode,
-		&file.UID,
-		&file.GID,
-		&linkTarget,
-	)
+	file, err := r.scanFile(tx.QueryRowContext(ctx, query, path))
 	LogSQL("GetByPathTx Scan complete", query, path)

 	if err == sql.ErrNoRows {
@@ -164,10 +116,80 @@ func (r *FileRepository) GetByPathTx(ctx context.Context, tx *sql.Tx, path strin
 		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 = linkTarget.String
+		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
@@ -175,7 +197,7 @@ func (r *FileRepository) GetByPathTx(ctx context.Context, tx *sql.Tx, path strin

 func (r *FileRepository) ListModifiedSince(ctx context.Context, since time.Time) ([]*File, error) {
 	query := `
-		SELECT id, path, mtime, ctime, size, mode, uid, gid, link_target
+		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
 		FROM files
 		WHERE mtime >= ?
 		ORDER BY path
@@ -189,32 +211,11 @@ func (r *FileRepository) ListModifiedSince(ctx context.Context, since time.Time)

 	var files []*File
 	for rows.Next() {
-		var file File
-		var mtimeUnix, ctimeUnix int64
-		var linkTarget sql.NullString
-
-		err := rows.Scan(
-			&file.ID,
-			&file.Path,
-			&mtimeUnix,
-			&ctimeUnix,
-			&file.Size,
-			&file.Mode,
-			&file.UID,
-			&file.GID,
-			&linkTarget,
-		)
+		file, err := r.scanFileRows(rows)
 		if err != nil {
 			return nil, fmt.Errorf("scanning file: %w", err)
 		}
-
-		file.MTime = time.Unix(mtimeUnix, 0)
-		file.CTime = time.Unix(ctimeUnix, 0)
-		if linkTarget.Valid {
-			file.LinkTarget = linkTarget.String
-		}
-
-		files = append(files, &file)
+		files = append(files, file)
 	}

 	return files, rows.Err()
@@ -238,14 +239,14 @@ func (r *FileRepository) Delete(ctx context.Context, tx *sql.Tx, path string) er
 }

 // DeleteByID deletes a file by its UUID
-func (r *FileRepository) DeleteByID(ctx context.Context, tx *sql.Tx, id string) error {
+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)
+		_, err = tx.ExecContext(ctx, query, id.String())
 	} else {
-		_, err = r.db.ExecWithLog(ctx, query, id)
+		_, err = r.db.ExecWithLog(ctx, query, id.String())
 	}

 	if err != nil {
@@ -257,7 +258,7 @@ func (r *FileRepository) DeleteByID(ctx context.Context, tx *sql.Tx, id string)

 func (r *FileRepository) ListByPrefix(ctx context.Context, prefix string) ([]*File, error) {
 	query := `
-		SELECT id, path, mtime, ctime, size, mode, uid, gid, link_target
+		SELECT id, path, source_path, mtime, ctime, size, mode, uid, gid, link_target
 		FROM files
 		WHERE path LIKE ? || '%'
 		ORDER BY path
@@ -271,32 +272,37 @@ func (r *FileRepository) ListByPrefix(ctx context.Context, prefix string) ([]*Fi

 	var files []*File
 	for rows.Next() {
-		var file File
-		var mtimeUnix, ctimeUnix int64
-		var linkTarget sql.NullString
-
-		err := rows.Scan(
-			&file.ID,
-			&file.Path,
-			&mtimeUnix,
-			&ctimeUnix,
-			&file.Size,
-			&file.Mode,
-			&file.UID,
-			&file.GID,
-			&linkTarget,
-		)
+		file, err := r.scanFileRows(rows)
 		if err != nil {
 			return nil, fmt.Errorf("scanning file: %w", err)
 		}
+		files = append(files, file)
+	}

-		file.MTime = time.Unix(mtimeUnix, 0)
-		file.CTime = time.Unix(ctimeUnix, 0)
-		if linkTarget.Valid {
-			file.LinkTarget = linkTarget.String
+	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)
+		files = append(files, file)
 	}

 	return files, rows.Err()
@@ -309,7 +315,7 @@ func (r *FileRepository) CreateBatch(ctx context.Context, tx *sql.Tx, files []*F
 		return nil
 	}

-	// Each File has 9 values, so batch at 100 to be safe with SQLite's variable limit
+	// 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 {
@@ -319,16 +325,17 @@ func (r *FileRepository) CreateBatch(ctx context.Context, tx *sql.Tx, files []*F
 		}
 		batch := files[i:end]

-		query := `INSERT INTO files (id, path, mtime, ctime, size, mode, uid, gid, link_target) VALUES `
-		args := make([]interface{}, 0, len(batch)*9)
+		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, f.Path, f.MTime.Unix(), f.CTime.Unix(), f.Size, f.Mode, f.UID, f.GID, f.LinkTarget)
+			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,
@@ -354,9 +361,9 @@ func (r *FileRepository) CreateBatch(ctx context.Context, tx *sql.Tx, files []*F
 // DeleteOrphaned deletes files that are not referenced by any snapshot
 func (r *FileRepository) DeleteOrphaned(ctx context.Context) error {
 	query := `
-		DELETE FROM files 
+		DELETE FROM files
 		WHERE NOT EXISTS (
-			SELECT 1 FROM snapshot_files 
+			SELECT 1 FROM snapshot_files
 			WHERE snapshot_files.file_id = files.id
 		)
 	`