Escape the database path in the SQLite connection string (closes #55)
check / check (push) Failing after 2s

openDB put the path into the connection string unescaped, so a ? or #
in it ended the file name and a % started an escape: scan could
silently fill a database under a shortened name. The path now goes
through net/url as a file: URI. An absolute path gets an empty host and
a relative path none, because SQLite reads what follows file:// up to
the next slash as a host name. The path is not cleaned, so it stays
exactly what the operator gave.

A test runs scan, report and trees against such a file name given as an
absolute path, as one starting with //, and as a relative path, and
checks that only that file and its lock file exist afterwards.

Model: opus-5-5
This commit was merged in pull request #87.
This commit is contained in:
2026-10-04 15:13:19 +02:00
parent c9c8b1d06c
commit 722675f153
4 changed files with 88 additions and 2 deletions
+68
View File
@@ -8,6 +8,7 @@ import (
"io/fs"
"os"
"path/filepath"
"slices"
"strconv"
"strings"
"testing"
@@ -639,6 +640,73 @@ func TestRunReportsNeedOnlyReadAccess(t *testing.T) {
}
}
// assertRunsUseDatabase runs scan, then report and trees, against the
// database that SFDUPES_DATABASE names, the file name in dir. It fails
// unless the reports find the duplicate pair the scan recorded and dir
// then holds only that file and its lock file: nothing was created
// under a shortened name.
func assertRunsUseDatabase(t *testing.T, dir, name string) {
t.Helper()
dupes := scanFixture(t)
want := "first\tdupe\tsize\n" + dupes[0] + "\t" + dupes[1] + "\t300\n"
if got := runStdout(t, cmdReport); got != want {
t.Errorf("report stdout = %q, want %q", got, want)
}
want = "first\tdupe\tfiles\tsize\n" +
filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
if got := runStdout(t, cmdTrees); got != want {
t.Errorf("trees stdout = %q, want %q", got, want)
}
entries, err := os.ReadDir(dir)
if err != nil {
t.Fatal(err)
}
got := make([]string, 0, len(entries))
for _, e := range entries {
got = append(got, e.Name())
}
if wantFiles := []string{name, name + ".lock"}; !slices.Equal(got, wantFiles) {
t.Errorf("%s holds %q, want %q", dir, got, wantFiles)
}
}
func TestRunDatabasePathUsedAsGiven(t *testing.T) {
// README §Database: the path names the database file exactly. In
// SQLite's connection string an unescaped ? or # would end the file
// name and % would start an escape, and a path starting with //
// could be read as a host name. %25 is a valid escape, so unescaped
// this name opens a file named a without any error.
const name = "a?b#c%25d e.sqlite"
t.Run("absolute", func(t *testing.T) {
dir := t.TempDir()
t.Setenv(databaseEnv, filepath.Join(dir, name))
assertRunsUseDatabase(t, dir, name)
})
t.Run("leading double slash", func(t *testing.T) {
dir := t.TempDir()
t.Setenv(databaseEnv, "/"+filepath.Join(dir, name))
assertRunsUseDatabase(t, dir, name)
})
t.Run("relative", func(t *testing.T) {
dir := t.TempDir()
t.Chdir(dir)
t.Setenv(databaseEnv, name)
assertRunsUseDatabase(t, dir, name)
})
}
// holdScanLock takes the lock on the database at path, as a running
// scan does, and holds it until the test ends. It fails the test when
// the lock is already held.