Merge pull request 'next into main: the command moves to cmd/sfdupes' (#159) from next into main

Reviewed-on: #159

README.md

@@ -29,6 +29,7 @@ first look at a new machine with one command.
 
 ```sh
 make build
+export SFDUPES_DATABASE="$HOME/.local/share/sfdupes/db.sqlite"
 ./sfdupes scan /srv
 ./sfdupes report > dupes.tsv
 ./sfdupes trees > dupetrees.tsv
@@ -44,9 +45,8 @@ that stands for a piece of hardware, such as a disk or a terminal. `report`
 prints the file-level duplicates. `trees` prints the duplicate directory trees.
 `info` prints the database's path, size and record count.
 
-Root keeps the database in `/var/lib/sfdupes/db.sqlite`. On Linux, any other
-user keeps it in `~/.local/state/sfdupes/db.sqlite`. `SFDUPES_DATABASE` names
-another file (see "Location"). The first `scan` creates the database.
+The database is `/var/lib/sfdupes/db.sqlite` unless `SFDUPES_DATABASE` names
+another file. The first `scan` creates it.
 
 `report`, `trees` and `info` write their data to stdout. Progress, warnings and
 errors go to stderr. stdout and stderr are a program's two output streams. The
@@ -146,9 +146,8 @@ walk"). As the file `/etc/cron.d/sfdupes`:
 - `report`, `trees` and `info` need only read access to the database. The umask
   is the setting that removes permissions from the files a process creates.
   Under the usual umask of `022`, the first scan creates the database readable
-  by every user. Another user can then run those three commands against root's
-  database, with `SFDUPES_DATABASE=/var/lib/sfdupes/db.sqlite` before the
-  command.
+  by every user. An unprivileged user can then run those three commands against
+  root's database.
 
 ### Reading the reports
 
@@ -284,9 +283,9 @@ The reference below is also the program's specification.
 ### Settings
 
 - `SFDUPES_DATABASE` names the database file. When it is unset or empty, the
-  database is at its default path (see "Location"). There is no command-line
-  flag for it. The path names the file exactly, whatever characters it holds. A
-  relative path is relative to the working directory.
+  database is `/var/lib/sfdupes/db.sqlite`. There is no command-line flag for
+  it. The path names the file exactly, whatever characters it holds. A relative
+  path is relative to the working directory.
 - `--workers N` (`scan`) sets how many directories `scan` reads at once while it
   lists the trees. It also sets how many files `scan` reads at once while it
   hashes them. The default is the number of CPUs. `N` must be at least 1. A
@@ -666,7 +665,6 @@ Processing:
 - Records are grouped by signature, the four values
   `(size, head, tail, content)`.
 - Every group with two or more paths is a duplicate group.
-- Empty files form no group, because removing one frees nothing.
 - Within a group, paths are sorted in byte order. The first is `first`, and
   every other path is a `dupe`.
 - Groups are ordered by size, largest first, then by `first` path. The output is
@@ -715,7 +713,7 @@ The summary line on stderr gives:
 - the reclaimable bytes, the sum of `size` over all rows.
 
 ```
-report: 14 records read, 4 duplicate groups, 7 dupe files, 10.0 KiB reclaimable
+report: 14 records read, 5 duplicate groups, 8 dupe files, 10.0 KiB reclaimable
 ```
 
 ### `trees` mode
@@ -743,9 +741,6 @@ Processing:
 - `trees` builds the directory tree and computes every directory's digest. It
   then groups the directories by digest. Every group with two or more
   directories is a duplicate-tree group.
-- `trees` leaves out a group whose trees hold 0 bytes, because removing one
-  frees nothing. An empty file still counts toward the digest of a tree that
-  holds other files.
 - `trees` leaves out a group that a group of its members' parents already
   implies. A group is left out when its members' parents are distinct
   directories that all have the same digest. The parents' group, or an
@@ -881,15 +876,7 @@ All five subcommands work on one SQLite database file.
 #### Location
 
 The database is the file named by `SFDUPES_DATABASE`, when that is set and not
-empty. Otherwise it is at its default path, which depends on the user:
-
-- For root, it is `/var/lib/sfdupes/db.sqlite`.
-- For any other user, it is `sfdupes/db.sqlite` in the XDG state directory. That
-  directory is `$XDG_STATE_HOME` when that is set to an absolute path. Otherwise
-  it is `~/.local/state` on Linux and `~/Library/Application Support` on macOS.
-
-All five subcommands use the same default, so a user's `report` reads the
-database that user's `scan` wrote.
+empty, and otherwise `/var/lib/sfdupes/db.sqlite`.
 
 Each subcommand prints one line on stderr naming the database it uses, before
 anything else and whether or not stderr is a terminal. The line gives the path
@@ -929,9 +916,9 @@ Only one `scan` at a time can hold the lock.
 - For its whole run, `scan` holds a lock on a lock file beside the database. The
   lock is taken with the `flock(2)` system call, a request a program makes to
   the kernel, and only one process can hold it. The lock file's name is the
-  database's path, with symlinks resolved, plus `.lock`. For root, by default,
-  that is `/var/lib/sfdupes/db.sqlite.lock`. A path through a symlink names the
-  same lock file.
+  database's path, with symlinks resolved, plus `.lock`. By default that is
+  `/var/lib/sfdupes/db.sqlite.lock`. A path through a symlink names the same
+  lock file.
 - `scan` takes the lock before it walks the filesystem or opens the database.
   Just before that, it creates the database file, empty, if it is missing. So
   the lock file is named the same way before the first scan as after. A symlink
@@ -1395,7 +1382,7 @@ All of the following, run in this directory, must pass:
     head -c 2000 /dev/urandom > "$d/a/unique.bin"     # same size, different content
     printf 'x' > "$d/tiny1"; printf 'x' > "$d/tiny2"  # 1-byte duplicates
     printf 'y' > "$d/tiny3"                           # 1-byte non-duplicate
-    : > "$d/empty1"; : > "$d/empty2"                  # empty files
+    : > "$d/empty1"; : > "$d/empty2"                  # empty duplicates
     # duplicate trees: t1 and t2 are identical; t3 differs by one filename
     mkdir -p "$d/t1/sub" "$d/t2/sub" "$d/t3/sub"
     head -c 3000 /dev/urandom > "$d/t1/f1"
@@ -1420,8 +1407,8 @@ All of the following, run in this directory, must pass:
       is the path that sorts first.
     - `t1/f1`, `t2/f1` and `t3/f1` form one group.
     - `t1/sub/f2`, `t2/sub/f2` and `t3/sub/f2renamed` form one group.
-    - `tiny1` and `tiny2` form a pair.
-    - `unique.bin`, `tiny3`, `empty1` and `empty2` appear nowhere.
+    - `tiny1` and `tiny2` form a pair, and so do `empty1` and `empty2`.
+    - `unique.bin` and `tiny3` appear nowhere.
     - The groups come in order of size, largest first.
 
     `trees` prints exactly one row, `$d/t1` as `first` and `$d/t2` as `dupe`.

TODO.md

@@ -29,15 +29,6 @@
 Newest first. An entry ends with its date and its issue or branch, where those
 are known.
 
-- Without `SFDUPES_DATABASE`, a user other than root keeps the database in
-  `sfdupes/db.sqlite` under the XDG state directory, `~/.local/state` by
-  default. Root keeps `/var/lib/sfdupes/db.sqlite`. `sfdupes --help` says where
-  the database is (2026-11-11, https://git.eeqj.de/sneak/sfdupes/issues/171)
-
-- `report` and `trees` leave out empty files. `report` writes no group of size
-  0, and `trees` writes no group whose trees hold 0 bytes. An empty file still
-  counts toward a tree's digest (2026-11-11,
-  https://git.eeqj.de/sneak/sfdupes/issues/178)
 - The Go code moved out of the repository root. `cmd/sfdupes/main.go` is the
   command, and it calls `Main` in the package `internal/sfdupes`. `main.go`
   became `internal/sfdupes/cli.go`. Every other file kept its name. The install

cmd/sfdupes/main.go

@@ -5,10 +5,8 @@
 // KiB, and of the content. The content hash covers the whole file under
 // 100 MiB, and 1 MiB at each gigabyte at 100 MiB or more, so a large
 // file is never read in full. scan maintains a persistent SQLite
-// database of file signatures that the other subcommands read. The
-// database is SFDUPES_DATABASE, or by default /var/lib/sfdupes/db.sqlite
-// for root and sfdupes/db.sqlite in the XDG state directory for any
-// other user.
+// database of file signatures (SFDUPES_DATABASE, default
+// /var/lib/sfdupes/db.sqlite) that the other subcommands read.
 //
 // Usage:
 //

go.mod

@@ -3,7 +3,6 @@ module sneak.berlin/go/sfdupes
 go 1.25.7
 
 require (
-	github.com/adrg/xdg v0.5.3
 	github.com/schollz/progressbar/v3 v3.19.1
 	github.com/spf13/cobra v1.10.2
 	golang.org/x/sys v0.46.0

go.sum

@@ -1,5 +1,3 @@
-github.com/adrg/xdg v0.5.3 h1:xRnxJXne7+oWDatRhR1JLnvuccuIeCoBu2rtuLqQB78=
-github.com/adrg/xdg v0.5.3/go.mod h1:nlTsY+NNiCBGCK2tpm09vRqfVzrc2fLmXGpBLF0zlTQ=
 github.com/chengxilo/virtualterm v1.0.4 h1:Z6IpERbRVlfB8WkOmtbHiDbBANU7cimRIof7mk9/PwM=
 github.com/chengxilo/virtualterm v1.0.4/go.mod h1:DyxxBZz/x1iqJjFxTFcr6/x+jSpqN0iwWCOK1q10rlY=
 github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=

internal/sfdupes/cli.go

@@ -116,13 +116,6 @@ func run(args []string, stdout, stderr io.Writer) int {
 	}
 }
 
-// databaseHelp says in sfdupes --help where the database is.
-const databaseHelp = `The database is the file SFDUPES_DATABASE names.
-When that is unset or empty, root uses /var/lib/sfdupes/db.sqlite. Any
-other user uses sfdupes/db.sqlite in the XDG state directory:
-$XDG_STATE_HOME, or ~/.local/state when that is unset
-(~/Library/Application Support on macOS).`
-
 // newRootCommand builds the command tree. Everything on stdout is
 // machine-readable data, the version line included; all human-facing
 // output (help, usage, errors) goes to stderr.
@@ -141,12 +134,9 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 		return nil
 	})
 
-	short := "Find candidate duplicate files by size and head/tail/content SHA-256"
-
 	root := &cobra.Command{
 		Use:   "sfdupes",
-		Short: short,
-		Long:  short + ".\n\n" + databaseHelp,
+		Short: "Find candidate duplicate files by size and head/tail/content SHA-256",
 		Args:  cobra.NoArgs,
 		RunE: func(cmd *cobra.Command, args []string) error {
 			if showVersion {

internal/sfdupes/cli_test.go

@@ -15,7 +15,6 @@ import (
 	"strings"
 	"testing"
 
-	"github.com/adrg/xdg"
 	"golang.org/x/sys/unix"
 )
 
@@ -554,14 +553,13 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 	// line.
 	t.Setenv(databaseEnv, "")
 
-	dbPath := defaultDatabasePath(os.Geteuid())
-
 	// Whether scan calls the database new depends on that machine too.
-	scanWant := "scan: database " + dbPath + " (default)\n"
+	scanWant := "scan: database " + defaultDatabasePath + " (default)\n"
 
-	_, err := os.Stat(dbPath)
+	_, err := os.Stat(defaultDatabasePath)
 	if errors.Is(err, fs.ErrNotExist) {
-		scanWant = "scan: new database " + dbPath + " (default)\n"
+		scanWant = "scan: new database " + defaultDatabasePath +
+			" (default)\n"
 	}
 
 	missing := filepath.Join(t.TempDir(), "nope")
@@ -580,21 +578,21 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 			run: func() error {
 				return runReport(cancelledContext(t), io.Discard)
 			},
-			want: "report: database " + dbPath + " (default)\n" +
+			want: "report: database " + defaultDatabasePath + " (default)\n" +
 				reportOpenLine + "\n" + reportOpenLine + "\n",
 		},
 		cmdTrees: {
 			run: func() error {
 				return runTrees(cancelledContext(t), io.Discard)
 			},
-			want: "trees: database " + dbPath + " (default)\n" +
+			want: "trees: database " + defaultDatabasePath + " (default)\n" +
 				treesOpenLine + "\n" + treesOpenLine + "\n",
 		},
 		cmdInfo: {
 			run: func() error {
 				return runInfo(cancelledContext(t), io.Discard)
 			},
-			want: "info: database " + dbPath + " (default)\n" +
+			want: "info: database " + defaultDatabasePath + " (default)\n" +
 				infoOpenLine + "\n" + infoOpenLine + "\n",
 		},
 	}
@@ -713,20 +711,6 @@ func TestRunHelp(t *testing.T) {
 			t.Errorf("run(%v) stdout = %q, want nothing (data only)",
 				args, got)
 		}
-
-		if args[0] == cmdScan {
-			continue
-		}
-
-		// README §Location: sfdupes --help says where the database is.
-		for _, want := range []string{
-			databaseEnv, rootDatabasePath, "XDG_STATE_HOME", "~/.local/state",
-		} {
-			if !strings.Contains(stderr.String(), want) {
-				t.Errorf("run(%v) stderr = %q, want it to name %q",
-					args, stderr.String(), want)
-			}
-		}
 	}
 }
 
@@ -1512,24 +1496,6 @@ func TestRunDatabasePathUsedAsGiven(t *testing.T) {
 	})
 }
 
-func TestRunNonRootUsesStateDirectory(t *testing.T) {
-	// README §Location: without SFDUPES_DATABASE, a user other than
-	// root keeps the database in the XDG state directory. scan creates
-	// the missing directories, and report and trees read the same file.
-	if os.Geteuid() == 0 {
-		t.Skip("root uses " + rootDatabasePath)
-	}
-
-	t.Cleanup(xdg.Reload)
-
-	state := t.TempDir()
-	t.Setenv("XDG_STATE_HOME", state)
-	t.Setenv(databaseEnv, "")
-	xdg.Reload()
-
-	assertRunsUseDatabase(t, filepath.Join(state, "sfdupes"), "db.sqlite")
-}
-
 // 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.

internal/sfdupes/db.go

@@ -15,16 +15,15 @@ import (
 	"strings"
 	"time"
 
-	"github.com/adrg/xdg"
 	"golang.org/x/sys/unix"
 	// The pure-Go SQLite driver, registered as "sqlite"; keeps cgo
 	// disabled.
 	_ "modernc.org/sqlite"
 )
 
-// rootDatabasePath is the database root uses when SFDUPES_DATABASE is
-// not set.
-const rootDatabasePath = "/var/lib/sfdupes/db.sqlite"
+// defaultDatabasePath is where the persistent scan database lives when
+// SFDUPES_DATABASE is not set.
+const defaultDatabasePath = "/var/lib/sfdupes/db.sqlite"
 
 // databaseEnv is the environment variable that overrides the database
 // path.
@@ -145,27 +144,13 @@ var errScanRunning = errors.New("another scan is running")
 // 32 bytes of a SHA-256.
 var errHashSize = errors.New("hash is not 32 bytes")
 
-// defaultDatabasePath is the database used when SFDUPES_DATABASE is not
-// set: rootDatabasePath for root (euid 0), and db.sqlite in the
-// directory sfdupes under the XDG state directory for any other user.
-// xdg reads XDG_STATE_HOME and HOME once, when the program starts. The
-// path is joined as text, not cleaned, for the reason absolutePath
-// gives.
-func defaultDatabasePath(euid int) string {
-	if euid == 0 {
-		return rootDatabasePath
-	}
-
-	return strings.TrimSuffix(xdg.StateHome, "/") + "/sfdupes/db.sqlite"
-}
-
 // databasePath resolves the database location: SFDUPES_DATABASE when
-// set and non-empty, defaultDatabasePath otherwise. It returns the
+// set and non-empty, the compiled-in default otherwise. It returns the
 // path, made absolute by absolutePath, and where the path came from,
 // "default" or "from SFDUPES_DATABASE", for the line each subcommand
 // prints first on stderr.
 func databasePath() (string, string, error) {
-	path, source := defaultDatabasePath(os.Geteuid()), "default"
+	path, source := defaultDatabasePath, "default"
 	if p := os.Getenv(databaseEnv); p != "" {
 		path, source = p, "from "+databaseEnv
 	}

internal/sfdupes/db_test.go

@@ -9,13 +9,10 @@ import (
 	"io/fs"
 	"os"
 	"path/filepath"
-	"runtime"
 	"slices"
 	"strings"
 	"testing"
 	"time"
-
-	"github.com/adrg/xdg"
 )
 
 // testDBPath returns a database path inside a fresh temp dir, with
@@ -63,7 +60,7 @@ func TestDatabasePath(t *testing.T) {
 	cases := []struct {
 		env, path, source string
 	}{
-		{"", defaultDatabasePath(os.Geteuid()), "default"},
+		{"", defaultDatabasePath, "default"},
 		{"/custom/place.sqlite", "/custom/place.sqlite", fromEnv},
 		{"/custom/link/../place.sqlite", "/custom/link/../place.sqlite",
 			fromEnv},
@@ -92,41 +89,6 @@ func TestDatabasePath(t *testing.T) {
 	}
 }
 
-func TestDefaultDatabasePath(t *testing.T) {
-	// README §Location: root's database is /var/lib/sfdupes/db.sqlite.
-	// Any other user's is db.sqlite in sfdupes under XDG_STATE_HOME, or
-	// under ~/.local/state when XDG_STATE_HOME is unset or not absolute.
-	if runtime.GOOS != goosLinux {
-		t.Skip("macOS has another default state directory")
-	}
-
-	t.Cleanup(xdg.Reload)
-	t.Setenv("HOME", "/home/someone")
-
-	cases := []struct {
-		euid      int
-		stateHome string
-		want      string
-	}{
-		{0, "", rootDatabasePath},
-		{0, "/elsewhere/state", rootDatabasePath},
-		{1000, "", "/home/someone/.local/state/sfdupes/db.sqlite"},
-		{1000, "relative/state", "/home/someone/.local/state/sfdupes/db.sqlite"},
-		{1000, "/elsewhere/state", "/elsewhere/state/sfdupes/db.sqlite"},
-		{1000, "/elsewhere/state/", "/elsewhere/state/sfdupes/db.sqlite"},
-	}
-
-	for _, tc := range cases {
-		t.Setenv("XDG_STATE_HOME", tc.stateHome)
-		xdg.Reload()
-
-		if got := defaultDatabasePath(tc.euid); got != tc.want {
-			t.Errorf("defaultDatabasePath(%d) with XDG_STATE_HOME=%q = %q, want %q",
-				tc.euid, tc.stateHome, got, tc.want)
-		}
-	}
-}
-
 func TestOpenScanDatabaseCreates(t *testing.T) {
 	t.Parallel()
 

internal/sfdupes/report.go

@@ -195,11 +195,10 @@ func (w *reportWriter) add(r scanRec) error {
 }
 
 // endGroup ends the paths read with w.sig: two or more are a duplicate
-// group, held with its paths sorted until writeGroups writes it. Empty
-// files form no group, since removing one frees nothing.
+// group, held with its paths sorted until writeGroups writes it.
 func (w *reportWriter) endGroup() {
-	if len(w.paths) < minGroupSize || w.sig.size == 0 {
-		// The paths are dropped, and their slice reused.
+	if len(w.paths) < minGroupSize {
+		// A path with no duplicate is dropped, and its slice reused.
 		w.paths = w.paths[:0]
 
 		return

internal/sfdupes/report_test.go

@@ -434,27 +434,6 @@ func TestDupeGroups(t *testing.T) {
 	}
 }
 
-// TestDupeGroupsLeavesOutEmptyFiles checks that empty files form no
-// duplicate group, while 1-byte files still do.
-func TestDupeGroupsLeavesOutEmptyFiles(t *testing.T) {
-	t.Parallel()
-
-	e, x := sha256.Sum256(nil), testHash("x")
-	recs := []scanRec{
-		{size: 0, head: e, tail: e, content: e, path: "/a/.gitkeep"},
-		{size: 0, head: e, tail: e, content: e, path: "/b/.gitkeep"},
-		{size: 0, head: e, tail: e, content: e, path: "/c/__init__.py"},
-		{size: 1, head: x, tail: x, content: x, path: "/tiny1"},
-		{size: 1, head: x, tail: x, content: x, path: "/tiny2"},
-	}
-
-	groups := dupeGroupsOf(t, recs)
-	if len(groups) != 1 || groups[0].size != 1 ||
-		!slices.Equal(groups[0].paths, []string{"/tiny1", "/tiny2"}) {
-		t.Fatalf("groups = %+v, want only /tiny1 /tiny2 of size 1", groups)
-	}
-}
-
 func TestDupeGroupsContentSeparates(t *testing.T) {
 	t.Parallel()
 

internal/sfdupes/scan_test.go

@@ -1185,12 +1185,11 @@ func assertSmokeDupeGroups(t *testing.T, dir string, db *sql.DB) {
 	t.Helper()
 
 	groups := dupeGroups(t, db)
-	if len(groups) != 4 {
-		t.Fatalf("len(groups) = %d, want 4", len(groups))
+	if len(groups) != 5 {
+		t.Fatalf("len(groups) = %d, want 5", len(groups))
 	}
 
-	// The empty files empty1 and empty2 form no group.
-	wantSizes := []int64{3000, 2000, 100, 1}
+	wantSizes := []int64{3000, 2000, 100, 1, 0}
 	for i, g := range groups {
 		if g.size != wantSizes[i] {
 			t.Errorf("groups[%d].size = %d, want %d",
@@ -2368,8 +2367,8 @@ func TestRunScanPassesOverDatabase(t *testing.T) {
 			report := runStdout(t, cmdReport)
 			if strings.Contains(report, "db.sqlite") ||
 				strings.Contains(report, hardLink) ||
-				!strings.Contains(report, filepath.Join(tree, "b")) {
-				t.Errorf("report = %q, want a and b and none of "+
+				!strings.Contains(report, filepath.Join(tree, "empty2")) {
+				t.Errorf("report = %q, want the empty files and none of "+
 					"the database's files", report)
 			}
 		})

internal/sfdupes/trees.go

@@ -301,9 +301,7 @@ func fileEntry(name string, r scanRec) string {
 // collectTreeGroups groups directories by digest, counting each one on
 // prog as it is grouped, and returns every maximal group with two or
 // more members, each group's members sorted by path, groups ordered by
-// tree size descending then by first path ascending. A group whose
-// trees hold 0 bytes is left out, since removing one frees nothing. The
-// groups it implies hold 0 bytes too, so leaving it out hides nothing.
+// tree size descending then by first path ascending.
 func collectTreeGroups(allDirs []*treeNode, super *treeNode,
 	prog *progress,
 ) [][]*treeNode {
@@ -317,9 +315,7 @@ func collectTreeGroups(allDirs []*treeNode, super *treeNode,
 	var dupes [][]*treeNode
 
 	for _, g := range groups {
-		// The members share a digest, so they share a total size.
-		if len(g) < minGroupSize || g[0].totalSize == 0 ||
-			suppressed(g, super) {
+		if len(g) < minGroupSize || suppressed(g, super) {
 			continue
 		}
 

internal/sfdupes/trees_test.go

@@ -2,7 +2,6 @@ package sfdupes //nolint:testpackage // checks the unexported treeNode results
 
 import (
 	"bytes"
-	"crypto/sha256"
 	"database/sql"
 	"os"
 	"slices"
@@ -436,35 +435,6 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
 	}
 }
 
-// TestCollectTreeGroupsLeavesOutEmptyTrees checks that directories
-// holding only empty files form no group, and that an empty file still
-// counts toward the digest of a tree that holds other files.
-func TestCollectTreeGroupsLeavesOutEmptyTrees(t *testing.T) {
-	t.Parallel()
-
-	h, tl, c, e := testHash("h"), testHash("t"), testHash("c"),
-		sha256.Sum256(nil)
-	recs := []scanRec{
-		{size: 0, head: e, tail: e, content: e, path: "/e/a/.gitkeep"},
-		{size: 0, head: e, tail: e, content: e, path: "/e/b/.gitkeep"},
-		{size: 10, head: h, tail: tl, content: c, path: "/p/x1/f"},
-		{size: 0, head: e, tail: e, content: e, path: "/p/x1/.gitkeep"},
-		{size: 10, head: h, tail: tl, content: c, path: "/p/x2/f"},
-		{size: 0, head: e, tail: e, content: e, path: "/p/x2/.gitkeep"},
-		// Without the empty file, /p/x3 is no copy of /p/x1.
-		{size: 10, head: h, tail: tl, content: c, path: "/p/x3/f"},
-	}
-
-	super, dirs := treeOf(t, recs)
-
-	got := groupPaths(collectTreeGroups(dirs, super, nil))
-
-	want := [][]string{{"/p/x1", "/p/x2"}}
-	if !slices.EqualFunc(got, want, slices.Equal) {
-		t.Fatalf("groups = %v, want %v", got, want)
-	}
-}
-
 func TestCollectTreeGroupsDifferingParents(t *testing.T) {
 	t.Parallel()