Open the downloaded snapshot database read-only, on a private temp dir (closes #162)
check / check (pull_request) Successful in 1m21s

Restore and deep verify used to open the decrypted snapshot database
read-write through the local-index constructor, which applied migrations
against whatever the file carried, and left the decrypted file in the
shared temp directory. A forged file could redefine what the restore
queries return, and an interrupted open left decrypted metadata on disk.

Add database.OpenReadOnly: opens the file read-only (mode=ro) with
query_only and trusted_schema=OFF, never applies schema files, and
refuses any file whose schema carries a trigger, view or virtual table
or lacks an expected table. Restore and deep verify now both use it.

Each command materializes the database inside its own private (0700)
temp directory and removes the whole directory on every return path, so
the decrypted file and any SQLite side files are always cleaned up.
Deep verify now also checks the error from closing the temp file.

pickNextDownload returns (FileID, bool), so a genuine file carrying the
nil UUID is no longer mistaken for "nothing left"; runRestoreLoop fails
with an error if any file is still pending when it can make no progress.

Model: opus-4-8
This commit is contained in:
2026-09-22 10:29:51 +00:00
parent b4654f8e52
commit 46c295acf3
7 changed files with 541 additions and 62 deletions
+130
View File
@@ -17,6 +17,7 @@ import (
"embed"
"errors"
"fmt"
"net/url"
"os"
"path/filepath"
"sort"
@@ -219,6 +220,135 @@ func openWithRecovery(ctx context.Context, path string) (*DB, error) {
return db, nil
}
// errUntrustedSnapshotSchema is returned when a downloaded snapshot
// database carries schema objects the real schema never defines, or is
// missing a table the restore and deep-verify queries read.
var errUntrustedSnapshotSchema = errors.New(
"downloaded snapshot database has an untrusted schema")
// snapshotReadOnlyDSN builds the driver DSN that opens a materialized
// snapshot database file read-only. mode=ro opens the file read-only at
// the OS level, query_only rejects any write the engine is asked to make,
// and trusted_schema=OFF refuses to run application code named in the
// schema. The file: URI form is required for the driver to honour the
// mode parameter.
func snapshotReadOnlyDSN(path string) string {
u := url.URL{
Scheme: "file",
Path: path,
RawQuery: "mode=ro&_pragma=query_only(true)&_pragma=trusted_schema(false)",
}
return u.String()
}
// OpenReadOnly opens an already-materialized SQLite file for read-only
// querying of a snapshot database downloaded from the store, used by
// restore and deep verify. Unlike New it never applies schema migrations
// and never writes: the connection is opened read-only with query_only
// and trusted_schema=OFF. It refuses any file whose schema carries a
// trigger, view or virtual table, or lacks an expected table, so a forged
// file cannot redefine what the restore queries return. The caller owns
// the file and must remove it.
func OpenReadOnly(ctx context.Context, path string) (*DB, error) {
conn, err := sql.Open("sqlite", snapshotReadOnlyDSN(path))
if err != nil {
return nil, fmt.Errorf("opening read-only database: %w", err)
}
configureConnPool(conn)
err = conn.PingContext(ctx)
if err != nil {
_ = conn.Close()
return nil, fmt.Errorf("opening read-only database: %w", err)
}
err = verifySnapshotSchema(ctx, conn)
if err != nil {
_ = conn.Close()
return nil, err
}
return &DB{conn: conn, path: path}, nil
}
// verifySnapshotSchema rejects a downloaded database whose schema is not
// the plain table set the real schema defines. Any trigger, view or
// virtual table, or a missing expected table, fails the open.
func verifySnapshotSchema(ctx context.Context, conn *sql.DB) error {
// expectedSnapshotTables are the tables the restore and deep-verify
// queries read. A downloaded database missing any of them is not a
// genuine snapshot database and is refused.
expectedSnapshotTables := []string{
"blob_chunks",
"blobs",
"chunks",
"file_chunks",
"files",
}
rows, err := conn.QueryContext(
ctx, "SELECT type, name, sql FROM sqlite_master")
if err != nil {
return fmt.Errorf("reading snapshot schema: %w", err)
}
defer func() { _ = rows.Close() }()
present := make(map[string]struct{})
for rows.Next() {
var objType, name string
var objSQL sql.NullString
err = rows.Scan(&objType, &name, &objSQL)
if err != nil {
return fmt.Errorf("reading snapshot schema: %w", err)
}
switch objType {
case "trigger", "view":
return fmt.Errorf(
"%w: unexpected %s %q", errUntrustedSnapshotSchema, objType, name)
case "table":
if isVirtualTableSQL(objSQL.String) {
return fmt.Errorf(
"%w: unexpected virtual table %q",
errUntrustedSnapshotSchema, name)
}
present[name] = struct{}{}
}
}
err = rows.Err()
if err != nil {
return fmt.Errorf("reading snapshot schema: %w", err)
}
for _, table := range expectedSnapshotTables {
if _, ok := present[table]; !ok {
return fmt.Errorf(
"%w: missing table %q", errUntrustedSnapshotSchema, table)
}
}
return nil
}
// isVirtualTableSQL reports whether a sqlite_master row's SQL defines a
// virtual table. Virtual tables are recorded with type 'table' but a
// "CREATE VIRTUAL TABLE" definition and can run module code, so they are
// refused alongside triggers and views.
func isVirtualTableSQL(createSQL string) bool {
return strings.HasPrefix(
strings.ToUpper(strings.TrimSpace(createSQL)), "CREATE VIRTUAL TABLE")
}
// NewTestDB creates an in-memory SQLite database for testing purposes.
// The database is automatically initialized with the schema and is ready
// for use. Each call creates a new independent database instance.