Resolve scan operands to their real paths (closes #144)

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

main_test.go

@@ -14,6 +14,8 @@ import (
 	"strconv"
 	"strings"
 	"testing"
+
+	"golang.org/x/sys/unix"
 )
 
 // usageMarker is the first line of cobra's usage text, which a usage
@@ -797,7 +799,7 @@ func TestRunVersionWriteFailureIsFatal(t *testing.T) {
 func scanFixture(t *testing.T) []string {
 	t.Helper()
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 
 	dupes := []string{
 		writeFile(t, dir, "one/a.bin", pattern(1, 300)),
@@ -867,7 +869,7 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 	writeFile(t, dir, "a.bin", pattern(1, 300))
 
 	// Same size as a.bin, so the scan reads it, and the read fails.
@@ -895,58 +897,278 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	assertNoSidecars(t, path)
 }
 
-func TestRunScanSkipsSymlinkOperand(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
+// realTempDir returns a new temporary directory by its real path, so
+// tests hold where the temporary directory is reached through a
+// symlink.
+func realTempDir(t *testing.T) string {
+	t.Helper()
 
-	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)
+	dir, err := filepath.EvalSymlinks(t.TempDir())
 	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"))
+	return dir
 }
 
+// symlink creates link pointing at target.
+func symlink(t *testing.T, target, link string) {
+	t.Helper()
+
+	err := os.Symlink(target, link)
+	if err != nil {
+		t.Fatal(err)
+	}
+}
+
+// TestRunScanFollowsSymlinkOperand scans link, a symlink to target.
+// The operand is scanned at its real path, and its file is recorded
+// there.
+func TestRunScanFollowsSymlinkOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "target/sub/f", pattern(1, 10))
+
+	link := filepath.Join(dir, "link")
+	symlink(t, filepath.Join(dir, "target"), link)
+
+	stderr := scanOK(t, link)
+
+	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		"0 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanWalksOperandUnderSymlinkOperand scans link and link/sub,
+// with link a symlink to target. Both resolve under target, so
+// target/sub is walked once, as part of target.
 func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
-	writeFile(t, dir, "target/sub/f", pattern(1, 10))
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "target/sub/f", pattern(1, 10))
 
 	link := filepath.Join(dir, "link")
+	symlink(t, filepath.Join(dir, "target"), link)
 
-	err := os.Symlink(filepath.Join(dir, "target"), link)
+	stderr := scanOK(t, link, filepath.Join(link, "sub"))
+
+	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		"0 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanWalksSymlinkedOperandBelowOperand is the case of
+// https://git.eeqj.de/sneak/sfdupes/issues/144: scan dir dir/link/sub,
+// with dir/link a symlink to a directory outside dir. The walk of dir
+// does not follow link, so dir/link/sub is walked on its own at its
+// real path, and the record an earlier scan stored there survives.
+func TestRunScanWalksSymlinkedOperandBelowOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	a := writeFile(t, dir, "a", pattern(1, 10))
+
+	outside := realTempDir(t)
+	f := writeFile(t, outside, "sub/f", pattern(2, 10))
+
+	symlink(t, outside, filepath.Join(dir, "link"))
+
+	scanOK(t, filepath.Join(outside, "sub"))
+
+	stderr := scanOK(t, dir, filepath.Join(dir, "link", "sub"))
+
+	summary := "scan: 2 files seen (1 added, 0 updated, 0 removed, " +
+		"1 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	want := []string{a, f}
+	slices.Sort(want)
+
+	if got := storedPaths(t, path); !slices.Equal(got, want) {
+		t.Errorf("records = %q, want %q", got, want)
+	}
+}
+
+// TestRunScanDropsSymlinkOperandInsideOperand scans dir and link, with
+// link, outside dir, a symlink to dir/real. link resolves inside dir,
+// so it is dropped as covered by dir, and its file is recorded once.
+func TestRunScanDropsSymlinkOperandInsideOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "real/f", pattern(1, 10))
+
+	link := filepath.Join(realTempDir(t), "link")
+	symlink(t, filepath.Join(dir, "real"), link)
+
+	stderr := scanOK(t, dir, link)
+
+	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		"0 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanDanglingSymlinkOperandIsFatal scans a valid directory and
+// a symlink whose target does not exist. The scan fails with exit 1 and
+// an error naming the symlink as given, before it walks anything, so no
+// database is created.
+func TestRunScanDanglingSymlinkOperandIsFatal(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	writeFile(t, dir, "f", pattern(1, 10))
+
+	dangling := filepath.Join(realTempDir(t), "dangling")
+	symlink(t, filepath.Join(dir, "missing"), dangling)
+
+	stdout := captureStdout(t)
+
+	var stderr bytes.Buffer
+
+	code := run([]string{cmdScan, dir, dangling}, os.Stdout, &stderr)
+	if code != exitFatal {
+		t.Errorf("run(scan %s %s) = %d, want %d", dir, dangling, code,
+			exitFatal)
+	}
+
+	assertFatalOutput(t, stderr.String(), stdout())
+
+	want := "sfdupes: resolve " + dangling + ": "
+	if !strings.Contains(stderr.String(), want) {
+		t.Errorf("stderr = %q, want %q", stderr.String(), want)
+	}
+
+	_, err := os.Stat(path)
+	if !errors.Is(err, fs.ErrNotExist) {
+		t.Errorf("database: stat error %v, want it missing", err)
+	}
+}
+
+// TestRunScanFromSymlinkedWorkingDirectoryRecordsRealPath runs scan .
+// after a cd through home/proj, a symlink to data/proj. The file is
+// recorded under data/proj, its real path.
+func TestRunScanFromSymlinkedWorkingDirectoryRecordsRealPath(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "data/proj/f", pattern(1, 10))
+
+	err := os.Mkdir(filepath.Join(dir, "home"), 0o750)
 	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"))
+	symlink(t, filepath.Join(dir, "data", "proj"),
+		filepath.Join(dir, "home", "proj"))
 
-	db, err := openDB(path, reportParams)
+	// t.Chdir also sets PWD to the path through the symlink, as a
+	// shell does after cd.
+	t.Chdir(filepath.Join(dir, "home", "proj"))
+
+	scanOK(t, ".")
+
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanFollowsSymlinkBeforeDotDot scans a path with a ".." after
+// home/proj, a symlink to data/proj: home/proj/.. from dir, and .. after
+// a cd through home/proj. As with realpath, the ".." counts from
+// data/proj, so data is scanned and home is not.
+func TestRunScanFollowsSymlinkBeforeDotDot(t *testing.T) {
+	for _, tc := range []struct{ wd, operand string }{
+		{"", "home/proj/.."},
+		{"home/proj", ".."},
+	} {
+		t.Run(tc.operand, func(t *testing.T) {
+			path := testDBPath(t)
+			t.Setenv(databaseEnv, path)
+
+			dir := realTempDir(t)
+			f := writeFile(t, dir, "data/proj/f", pattern(1, 10))
+			g := writeFile(t, dir, "data/g", pattern(2, 10))
+			writeFile(t, dir, "home/h", pattern(3, 10))
+			symlink(t, filepath.Join(dir, "data", "proj"),
+				filepath.Join(dir, "home", "proj"))
+
+			// t.Chdir also sets PWD to the path given, as a shell does
+			// after cd.
+			t.Chdir(filepath.Join(dir, tc.wd))
+
+			scanOK(t, tc.operand)
+
+			want := []string{f, g}
+			slices.Sort(want)
+
+			if got := storedPaths(t, path); !slices.Equal(got, want) {
+				t.Errorf("records = %q, want %q", got, want)
+			}
+		})
+	}
+}
+
+// TestRunScanSkipsSymlinkToFIFOOperand scans link, a symlink to a FIFO.
+// The scan warns about the FIFO by its real path, counts it as skipped,
+// and exits 0.
+func TestRunScanSkipsSymlinkToFIFOOperand(t *testing.T) {
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	dir := realTempDir(t)
+	fifo := filepath.Join(dir, "fifo")
+
+	err := unix.Mkfifo(fifo, 0o600)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	t.Cleanup(func() { _ = db.Close() })
+	link := filepath.Join(dir, "link")
+	symlink(t, fifo, link)
 
-	recordByPath(t, dbRecords(t, db), filepath.Join(link, "sub", "f"))
+	stderr := scanOK(t, link)
+
+	warning := "walk " + fifo + ": skipping FIFO 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)
+	}
 }
 
 func TestRunScanSkipsZFSOperand(t *testing.T) {
-	zfs := filepath.Join(t.TempDir(), ".zfs")
+	zfs := filepath.Join(realTempDir(t), ".zfs")
 	f := writeFile(t, zfs, "snapshot/hourly/f", pattern(1, 10))
 
 	// No scan records a file inside a .zfs directory, so the record
@@ -997,7 +1219,7 @@ func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 	hourly := filepath.Join(dir, ".zfs", "snapshot", "hourly")
 	writeFile(t, hourly, "f", pattern(1, 10))
 	f := writeFile(t, dir, "f", pattern(2, 10))
@@ -1041,23 +1263,19 @@ func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
 
 // TestRunScanSkipsOperandThroughSymlinkIntoZFS scans snaps/daily, where
 // snaps is a symlink to pool/.zfs/snapshot. The operand is warned about
-// by the path given, counted as skipped, and not walked.
+// by its real path, counted as skipped, and not walked.
 func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
 	t.Setenv(databaseEnv, testDBPath(t))
 
-	dir := t.TempDir()
+	dir := realTempDir(t)
 	writeFile(t, dir, "pool/.zfs/snapshot/daily/f", pattern(1, 10))
 
 	snaps := filepath.Join(dir, "snaps")
+	symlink(t, filepath.Join(dir, "pool", ".zfs", "snapshot"), snaps)
 
-	err := os.Symlink(filepath.Join(dir, "pool", ".zfs", "snapshot"), snaps)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	daily := filepath.Join(snaps, "daily")
-	stderr := scanOK(t, daily)
+	stderr := scanOK(t, filepath.Join(snaps, "daily"))
 
+	daily := filepath.Join(dir, "pool", ".zfs", "snapshot", "daily")
 	warning := "walk " + daily + ": skipping operand inside a .zfs directory\n"
 	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
 		"0 unchanged), 1 skipped\n"
@@ -1069,24 +1287,19 @@ func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
 }
 
 // TestRunScanWalksOperandThroughSymlink scans data/daily, where data is
-// a symlink to a directory outside any .zfs directory. The operand is
-// scanned as usual, and its file is recorded by the path given.
+// a symlink to pool/data. The operand is scanned as usual, and its file
+// is recorded by its real path.
 func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := t.TempDir()
-	writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
+	dir := realTempDir(t)
+	f := writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
 
 	data := filepath.Join(dir, "data")
+	symlink(t, filepath.Join(dir, "pool", "data"), data)
 
-	err := os.Symlink(filepath.Join(dir, "pool", "data"), data)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	daily := filepath.Join(data, "daily")
-	stderr := scanOK(t, daily)
+	stderr := scanOK(t, filepath.Join(data, "daily"))
 
 	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
 		"0 unchanged), 0 skipped\n"
@@ -1094,14 +1307,9 @@ func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
 		t.Errorf("stderr = %q, want %q", stderr, summary)
 	}
 
-	db, err := openDB(path, reportParams)
-	if err != nil {
-		t.Fatal(err)
+	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
 	}
-
-	t.Cleanup(func() { _ = db.Close() })
-
-	recordByPath(t, dbRecords(t, db), filepath.Join(daily, "f"))
 }
 
 func TestRunReportSucceeds(t *testing.T) {