Resolve scan operands to their real paths (closes #144)
check / check (push) Canceled after 0s

scan now resolves every operand with its symlinks followed before the
walk, and uses that real path for pruning, walking, records and
warnings. A relative operand is joined to the working directory as the
kernel reports it, so a ".." after a symlink counts from its target, as
with realpath. A symlink operand is scanned at its target instead of
skipped. An operand given through a symlink below another operand, to a
directory outside it, is walked on its own instead of dropped with its
records deleted. An operand that cannot be resolved is a fatal error
naming the operand as given. The walk itself still follows no symlink.

Model: opus-5-5
This commit is contained in:
2026-11-06 18:27:42 +00:00
parent f52bbe5d95
commit c6066afa6e
6 changed files with 381 additions and 165 deletions
+35 -28
View File
@@ -2310,33 +2310,24 @@ func TestUnderRoot(t *testing.T) {
}
// TestRunScanPassesOverDatabase scans a tree that holds the scan's own
// database, reached directly and through a symlinked directory. The
// walk passes over the database file, its -wal and -shm files and its
// .lock file with no line and no count, and the record an earlier scan
// left for the .lock file is deleted. A rescan of the unchanged tree
// updates nothing, and report lists none of the database's files.
// database, and in one case also a hard link to the database file. The
// walk knows the database's files by device ID and inode number, so it
// passes over the database file, its -wal and -shm files, its .lock
// file and the hard link with no line and no count. The record an
// earlier scan left for the .lock file is deleted. A rescan of the
// unchanged tree updates nothing, and report lists none of the
// database's files.
func TestRunScanPassesOverDatabase(t *testing.T) {
for _, viaSymlink := range []bool{false, true} {
t.Run(fmt.Sprintf("via symlink %v", viaSymlink), func(t *testing.T) {
base := t.TempDir()
tree := filepath.Join(base, "real", "tree")
operand := tree
for _, viaHardLink := range []bool{false, true} {
t.Run(fmt.Sprintf("via hard link %v", viaHardLink), func(t *testing.T) {
tree := realTempDir(t)
hardLink := filepath.Join(tree, "hardlink")
writeFile(t, tree, "a", pattern(1, 100))
writeFile(t, tree, "b", pattern(1, 100))
writeFile(t, tree, "empty1", nil)
writeFile(t, tree, "empty2", nil)
if viaSymlink {
err := os.Symlink(filepath.Join(base, "real"),
filepath.Join(base, "link"))
if err != nil {
t.Fatal(err)
}
operand = filepath.Join(base, "link", "tree")
}
dbPath := filepath.Join(tree, "db.sqlite")
t.Setenv(databaseEnv, dbPath)
@@ -2346,7 +2337,7 @@ func TestRunScanPassesOverDatabase(t *testing.T) {
}
err = applyChanges(t.Context(), db, []scanRec{
{path: filepath.Join(operand, "db.sqlite.lock")},
{path: filepath.Join(tree, "db.sqlite.lock")},
}, nil, nil)
if err != nil {
t.Fatal(err)
@@ -2354,16 +2345,29 @@ func TestRunScanPassesOverDatabase(t *testing.T) {
closeScanDatabase(t.Context(), db, dbPath)
assertScanSummary(t,
if viaHardLink {
err = os.Link(dbPath, hardLink)
if err != nil {
t.Fatal(err)
}
}
stderr := assertScanSummary(t,
"4 files seen (4 added, 0 updated, 1 removed, 0 unchanged)",
operand)
assertScanSummary(t,
tree)
stderr += assertScanSummary(t,
"4 files seen (0 added, 0 updated, 0 removed, 4 unchanged)",
operand)
tree)
if strings.Contains(stderr, hardLink) {
t.Errorf("scan stderr = %q, want no line naming %s",
stderr, hardLink)
}
report := runStdout(t, cmdReport)
if strings.Contains(report, "db.sqlite") ||
!strings.Contains(report, filepath.Join(operand, "empty2")) {
strings.Contains(report, hardLink) ||
!strings.Contains(report, filepath.Join(tree, "empty2")) {
t.Errorf("report = %q, want the empty files and none of "+
"the database's files", report)
}
@@ -2388,8 +2392,9 @@ func TestRunScanPassesOverDatabaseOperands(t *testing.T) {
// assertScanSummary scans operands and fails the test unless the
// summary line gives counts with nothing skipped, and the line naming
// the database is the only one that names one of its files.
func assertScanSummary(t *testing.T, counts string, operands ...string) {
// the database is the only one that names one of its files. It returns
// everything the scan printed to stderr.
func assertScanSummary(t *testing.T, counts string, operands ...string) string {
t.Helper()
stderr := scanOK(t, operands...)
@@ -2403,4 +2408,6 @@ func assertScanSummary(t *testing.T, counts string, operands ...string) {
t.Errorf("scan %q: stderr = %q, want only the line naming the "+
"database to name one of its files", operands, stderr)
}
return stderr
}