Warn about and skip non-regular and .zfs operands, keeping their records (closes #9)

A symlink, socket, FIFO or device-node operand, or a directory operand
named .zfs, was silently ignored yet stayed in the scanned operands, so
the update phase deleted every record stored beneath it. Such an
operand now gets a one-line warning, counts as skipped, and is dropped
before overlapping operands are pruned and the database index is
loaded: another operand beneath it is still scanned, and the records
beneath it count as outside the scanned operands and are not deleted,
unless it lies under another operand. The exit status stays 0. An
operand that turns into one of these after that check is warned about
and skipped by the walk instead. README "scan mode" and "Rules for the
walk" say so.

Model: opus-5-5

main_test.go

@@ -82,6 +82,50 @@ func makeReadOnly(t *testing.T, path string) {
 	})
 }
 
+// captureStderr redirects os.Stderr to a file for the rest of the test
+// and returns a function reading back everything written to it. scan
+// writes its warnings and summary straight to os.Stderr, not to the
+// stderr writer run is given.
+func captureStderr(t *testing.T) func() string {
+	t.Helper()
+
+	f, err := os.Create(filepath.Join(t.TempDir(), "stderr"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	saved := os.Stderr
+	os.Stderr = f
+
+	t.Cleanup(func() {
+		os.Stderr = saved
+
+		_ = f.Close()
+	})
+
+	return func() string {
+		// Read what has been written without disturbing the write
+		// offset, so the capture can be inspected more than once.
+		size, err := f.Seek(0, io.SeekCurrent)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		if size == 0 {
+			return ""
+		}
+
+		b := make([]byte, size)
+
+		_, err = f.ReadAt(b, 0)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		return string(b)
+	}
+}
+
 // brokenDatabase writes a database that opens cleanly and passes the
 // schema-version check but has no files table, so the first query
 // fails with the database already open: a fatal error on a path that
@@ -306,19 +350,31 @@ func scanFixture(t *testing.T) []string {
 		t.Fatal(err)
 	}
 
-	var stdout, stderr bytes.Buffer
+	scanOK(t, dir)
 
-	code := run([]string{cmdScan, dir}, &stdout, &stderr)
+	return dupes
+}
+
+// scanOK runs scan over operands, fails the test unless it exits 0 with
+// nothing on stdout, and returns everything it printed to stderr.
+func scanOK(t *testing.T, operands ...string) string {
+	t.Helper()
+
+	var stdout bytes.Buffer
+
+	stderr := captureStderr(t)
+
+	code := run(append([]string{cmdScan}, operands...), &stdout, os.Stderr)
 	if code != exitOK {
-		t.Fatalf("run(scan) = %d, want %d; stderr: %s",
-			code, exitOK, stderr.String())
+		t.Fatalf("run(scan %q) = %d, want %d; stderr: %s",
+			operands, code, exitOK, stderr())
 	}
 
 	if got := stdout.String(); got != "" {
 		t.Errorf("scan stdout = %q, want nothing (data only)", got)
 	}
 
-	return dupes
+	return stderr()
 }
 
 func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
@@ -329,6 +385,103 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	assertNoSidecars(t, path)
 }
 
+func TestRunScanSkipsSymlinkOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := t.TempDir()
+	writeFile(t, dir, "target/sub/f", pattern(1, 10))
+
+	link := filepath.Join(dir, "link")
+
+	err := os.Symlink(filepath.Join(dir, "target"), link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// Scanning a directory through the symlink stores a record beneath
+	// the symlink's own path for a file beneath its target.
+	scanOK(t, filepath.Join(link, "sub"))
+
+	assertOperandSkipped(t, path, link, "symlink",
+		filepath.Join(link, "sub", "f"))
+}
+
+func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := t.TempDir()
+	writeFile(t, dir, "target/sub/f", pattern(1, 10))
+
+	link := filepath.Join(dir, "link")
+
+	err := os.Symlink(filepath.Join(dir, "target"), link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// link is dropped as a symlink, but link/sub must still be scanned,
+	// not dropped as lying under link.
+	scanOK(t, link, filepath.Join(link, "sub"))
+
+	db, err := openDB(path, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	recordByPath(t, dbRecords(t, db), filepath.Join(link, "sub", "f"))
+}
+
+func TestRunScanSkipsZFSOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	zfs := filepath.Join(t.TempDir(), ".zfs")
+	snapshot := filepath.Join(zfs, "snapshot", "hourly")
+	f := writeFile(t, snapshot, "f", pattern(1, 10))
+
+	// An operand beneath a .zfs directory is walked, because it is not
+	// itself named .zfs.
+	scanOK(t, snapshot)
+
+	assertOperandSkipped(t, path, zfs, ".zfs directory", f)
+}
+
+// assertOperandSkipped scans operand alone and checks that it is skipped
+// as kind: a warning naming it, one skip in the summary, exit 0, and the
+// record for kept, which an earlier scan stored beneath operand, still
+// in the database at dbPath.
+func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
+	kept string,
+) {
+	t.Helper()
+
+	stderr := scanOK(t, operand)
+
+	warning := "walk " + operand + ": skipping " + kind + " operand\n"
+	if !strings.Contains(stderr, warning) {
+		t.Errorf("stderr = %q, want %q", stderr, warning)
+	}
+
+	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
+		"0 unchanged), 1 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	db, err := openDB(dbPath, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	recordByPath(t, dbRecords(t, db), kept)
+}
+
 func TestRunReportSucceeds(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)