Limit report and trees to given paths (closes #174)

report and trees take optional PATH operands and use only the records
at or below them. Operands are made absolute and cleaned as text, never
looked up on the filesystem; each reported copy is still checked on
disk. With operands, trees reports only directories at or below an
operand: any other directory lies above an operand and can hold unused
files, so its digest neither gets reported nor suppresses its
children's group. The summary still counts every record read.

Model: opus-5-5

internal/sfdupes/cli.go

@@ -32,6 +32,13 @@ const (
 	cmdDwim   = "dwim"
 )
 
+// operandsHelp explains the PATH operands of report and trees in their
+// help.
+const operandsHelp = "With PATH operands, only the records at or " +
+	"below them are used. A relative PATH is joined to the working " +
+	"directory. No PATH is looked up on the filesystem, so a symlink in " +
+	"one is not followed."
+
 // errNoSubcommand is returned by the root command when it is invoked
 // without a subcommand. That is a usage error, and the usage text
 // cobra prints for it is the whole message.
@@ -167,20 +174,24 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 		"print the version to stdout")
 
 	reportCmd := &cobra.Command{
-		Use:   cmdReport,
+		Use:   cmdReport + " [PATH...]",
 		Short: "Read the scan database and print the file-level duplicates report",
-		Args:  cobra.NoArgs,
-		RunE: runE(func(ctx context.Context, _ []string) error {
-			return runReport(ctx, stdout)
+		Long: "Read the scan database and print the file-level duplicates " +
+			"report.\n\n" + operandsHelp,
+		Args: cobra.ArbitraryArgs,
+		RunE: runE(func(ctx context.Context, args []string) error {
+			return runReport(ctx, args, stdout)
 		}),
 	}
 
 	treesCmd := &cobra.Command{
-		Use:   cmdTrees,
+		Use:   cmdTrees + " [PATH...]",
 		Short: "Read the scan database and print the duplicate-tree report",
-		Args:  cobra.NoArgs,
-		RunE: runE(func(ctx context.Context, _ []string) error {
-			return runTrees(ctx, stdout)
+		Long: "Read the scan database and print the duplicate-tree " +
+			"report.\n\n" + operandsHelp,
+		Args: cobra.ArbitraryArgs,
+		RunE: runE(func(ctx context.Context, args []string) error {
+			return runTrees(ctx, args, stdout)
 		}),
 	}
 

internal/sfdupes/cli_test.go

@@ -577,14 +577,14 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 		},
 		cmdReport: {
 			run: func() error {
-				return runReport(cancelledContext(t), io.Discard)
+				return runReport(cancelledContext(t), nil, io.Discard)
 			},
 			want: "report: database " + defaultDatabasePath + " (default)\n" +
 				reportOpenLine + "\n" + reportOpenLine + "\n",
 		},
 		cmdTrees: {
 			run: func() error {
-				return runTrees(cancelledContext(t), io.Discard)
+				return runTrees(cancelledContext(t), nil, io.Discard)
 			},
 			want: "trees: database " + defaultDatabasePath + " (default)\n" +
 				treesOpenLine + "\n" + treesOpenLine + "\n",
@@ -620,8 +620,6 @@ func TestRunUsageErrors(t *testing.T) {
 	}{
 		"no subcommand":      {[]string{}, usageMarker},
 		"scan without paths": {[]string{cmdScan}, usageMarker},
-		"report with args":   {[]string{cmdReport, "x"}, usageMarker},
-		"trees with args":    {[]string{cmdTrees, "x"}, usageMarker},
 		"info with args":     {[]string{cmdInfo, "x"}, usageMarker},
 		"dwim with args":     {[]string{cmdDwim, "x"}, usageMarker},
 		"unknown flag":       {[]string{cmdScan, "--nope", "/"}, usageMarker},
@@ -1766,9 +1764,13 @@ func TestStdoutWriteErrorPropagates(t *testing.T) {
 	scanFixture(t)
 
 	cases := map[string]func(context.Context, io.Writer) error{
-		cmdReport: runReport,
-		cmdTrees:  runTrees,
-		cmdInfo:   runInfo,
+		cmdReport: func(ctx context.Context, w io.Writer) error {
+			return runReport(ctx, nil, w)
+		},
+		cmdTrees: func(ctx context.Context, w io.Writer) error {
+			return runTrees(ctx, nil, w)
+		},
+		cmdInfo: runInfo,
 	}
 
 	for name, fn := range cases {

internal/sfdupes/dwim.go

@@ -26,7 +26,7 @@ func runDwim(ctx context.Context, root string, stdout io.Writer) error {
 		return err
 	}
 
-	err = runTrees(ctx, stdout)
+	err = runTrees(ctx, nil, stdout)
 	if err != nil {
 		return err
 	}

internal/sfdupes/report.go

@@ -9,6 +9,7 @@ import (
 	"io"
 	"io/fs"
 	"os"
+	"path/filepath"
 	"slices"
 	"strings"
 	"syscall"
@@ -44,10 +45,12 @@ func reportPhase(name string) string {
 }
 
 // runReport implements the report subcommand: it prints the file-level
-// duplicates report as TSV on stdout. Of the scanned filesystem it
-// only checks, with pathExists, that each path in a duplicate group is
-// still there. It names the database on stderr before it opens it. Any
-// database problem, including a missing database, is fatal.
+// duplicates report as TSV on stdout, from the records at or below the
+// operands in args, or from every record when args is empty. Of the
+// scanned filesystem it only checks, with pathExists, that each path in
+// a duplicate group is still there; it never looks up an operand. It
+// names the database on stderr before it opens it. Any database
+// problem, including a missing database, is fatal.
 //
 // The work runs in two phases, each under a progress display of its
 // own on stderr: open (open the database) and read (read the number of
@@ -55,7 +58,12 @@ func reportPhase(name string) string {
 // order, writing each size's duplicate groups to stdout once that size
 // is read; see readReport). Each display ends before the next phase
 // starts, and before an error is returned to be printed.
-func runReport(ctx context.Context, stdout io.Writer) error {
+func runReport(ctx context.Context, args []string, stdout io.Writer) error {
+	operands, err := cleanOperands(args)
+	if err != nil {
+		return err
+	}
+
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
@@ -87,7 +95,8 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 		label: reportPhase("read"), unit: "records", total: -1,
 		waitingFor: countingRecords, stalledOn: "db/disk/out",
 	})
-	report, err := readReport(ctx, db, dbPath, stdout, pathExists, prog)
+	report, err := readReport(ctx, db, dbPath, operands, stdout, pathExists,
+		prog)
 
 	prog.finish()
 
@@ -108,12 +117,14 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 // dbPath, as its total, then reads every record in signature order,
 // counting each on prog, and writes the report to stdout: the header
 // line, then the rows of each size's duplicate groups once that size is
-// read. A path for which exists returns false is left out of its group.
-// stdout may be the terminal prog is drawn on, so the lines go through
-// prog's writer. It returns what it wrote, with the totals for the
-// summary line.
+// read. Only the records that underOperand finds under operands join a
+// group, and a path for which exists returns false is left out of its
+// group. stdout may be the terminal prog is drawn on, so the lines go
+// through prog's writer. It returns what it wrote, with the totals for
+// the summary line.
 func readReport(ctx context.Context, db *sql.DB, dbPath string,
-	stdout io.Writer, exists func(path string) bool, prog *progress,
+	operands []string, stdout io.Writer, exists func(path string) bool,
+	prog *progress,
 ) (*reportWriter, error) {
 	out := prog.writer(stdout)
 	report := &reportWriter{out: out, exists: exists}
@@ -128,6 +139,12 @@ func readReport(ctx context.Context, db *sql.DB, dbPath string,
 	err = loadSignatureRows(ctx, db, prog.setTotal, func(r scanRec) error {
 		prog.increment()
 
+		report.records++
+
+		if !underOperand(r.path, operands) {
+			return nil
+		}
+
 		writeErr = report.add(r)
 
 		return writeErr
@@ -159,7 +176,7 @@ func readReport(ctx context.Context, db *sql.DB, dbPath string,
 // records of one size, so it holds only the duplicate groups of the
 // size being read, and writes them, ordered by first path, once a
 // record of a smaller size comes. It counts what the summary line
-// reports.
+// reports; readReport counts the records read.
 type reportWriter struct {
 	out io.Writer
 
@@ -179,8 +196,6 @@ type reportWriter struct {
 // its paths; any other ends them, and one of a smaller size first
 // writes the groups of the size before.
 func (w *reportWriter) add(r scanRec) error {
-	w.records++
-
 	if r.size == w.sig.size && r.head == w.sig.head &&
 		r.tail == w.sig.tail && r.content == w.sig.content {
 		w.paths = append(w.paths, r.path)
@@ -273,6 +288,46 @@ func pathExists(path string) bool {
 	return !errors.Is(err, fs.ErrNotExist) && !errors.Is(err, syscall.ENOTDIR)
 }
 
+// cleanOperands returns the operands of report or trees, each made
+// absolute by absolutePath and then cleaned. The records hold real
+// paths, with no "." or ".." element and no repeated or trailing
+// slash, so an operand is cleaned to match them. No operand is looked
+// up on the filesystem.
+func cleanOperands(args []string) ([]string, error) {
+	operands := make([]string, 0, len(args))
+
+	for _, a := range args {
+		abs, err := absolutePath(a)
+		if err != nil {
+			return nil, fmt.Errorf("resolve path %s: %w", escapePath(a), err)
+		}
+
+		operands = append(operands, filepath.Clean(abs))
+	}
+
+	return operands, nil
+}
+
+// underOperand reports whether path is one of operands or lies below
+// one of them. Each operand is clean and absolute, as cleanOperands
+// returns it. With no operands, a report covers the whole database, so
+// underOperand is true for every path.
+func underOperand(path string, operands []string) bool {
+	if len(operands) == 0 {
+		return true
+	}
+
+	for _, o := range operands {
+		// Only the root directory's clean path ends in "/".
+		dir := strings.TrimSuffix(o, "/") + "/"
+		if path == o || strings.HasPrefix(path, dir) {
+			return true
+		}
+	}
+
+	return false
+}
+
 // escapePath returns a path as it is written in a report column (README
 // "Report output format"): a backslash, tab, newline or carriage return
 // becomes \\, \t, \n or \r, and every other byte is kept as it is.

internal/sfdupes/report_test.go

@@ -102,7 +102,8 @@ func dupeGroups(t *testing.T, db *sql.DB) []dupeGroup {
 
 	var out bytes.Buffer
 
-	_, err := readReport(t.Context(), db, "", &out, everyPathExists, nil)
+	_, err := readReport(t.Context(), db, "", nil, &out, everyPathExists,
+		nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -148,6 +149,103 @@ func dupeGroupsOf(t *testing.T, recs []scanRec) []dupeGroup {
 	return dupeGroups(t, db)
 }
 
+// TestRunReportOperands runs report with operands on three copies of
+// one file, two of them under srv/photos, and a fourth copy in
+// srv/photos2, all in a new directory. Only the records at or below the
+// operands form the groups and the totals, however each operand is
+// written.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestRunReportOperands(t *testing.T) {
+	h := testHash("h")
+
+	recs := make([]scanRec, 0, 4)
+	for _, p := range []string{
+		"/a/copy", "/srv/photos/x", "/srv/photos/y", "/srv/photos2/z",
+	} {
+		recs = append(recs,
+			scanRec{size: 7, head: h, tail: h, content: h, path: p})
+	}
+
+	dir, recs := recsOnDisk(t, recs)
+	a, x, y, z := recs[0].path, recs[1].path, recs[2].path, recs[3].path
+
+	t.Setenv(databaseEnv, seedDatabase(t, recs))
+
+	header := "first\tdupe\tsize\n"
+	row := func(first, dupe string) string {
+		return first + "\t" + dupe + "\t7\n"
+	}
+	photos := header + row(x, y)
+
+	cases := map[string]struct {
+		operands []string
+		want     string
+		summary  string
+	}{
+		"directory": {[]string{dir + "/srv/photos"}, photos,
+			"1 duplicate groups, 1 dupe files, 7 B reclaimable"},
+		"trailing slash":  {[]string{dir + "/srv/photos/"}, photos, ""},
+		"dot and dot-dot": {[]string{dir + "/srv/./a/../photos"}, photos, ""},
+		"files":           {[]string{a, z}, header + row(a, z), ""},
+		"overlapping": {[]string{dir + "/srv", dir + "/srv/photos"},
+			header + row(x, y) + row(x, z), ""},
+		"root": {[]string{"/"},
+			header + row(a, x) + row(a, y) + row(a, z), ""},
+		"no record": {[]string{dir + "/srv/photo"}, header,
+			"0 duplicate groups, 0 dupe files, 0 B reclaimable"},
+	}
+
+	for name, tc := range cases {
+		t.Run(name, func(t *testing.T) {
+			var stdout bytes.Buffer
+
+			stderr := captureStderr(t)
+
+			code := run(append([]string{cmdReport}, tc.operands...),
+				&stdout, os.Stderr)
+			if code != exitOK {
+				t.Fatalf("run(report %q) = %d, want %d; stderr: %s",
+					tc.operands, code, exitOK, stderr())
+			}
+
+			if got := stdout.String(); got != tc.want {
+				t.Errorf("stdout = %q, want %q", got, tc.want)
+			}
+
+			// The records read are all four, whatever the operands.
+			summary := "report: 4 records read, " + tc.summary + "\n"
+			if got := stderr(); tc.summary != "" &&
+				!strings.HasSuffix(got, summary) {
+				t.Errorf("stderr = %q, want it to end %q", got, summary)
+			}
+		})
+	}
+}
+
+//nolint:paralleltest // t.Chdir changes the process-wide working directory
+func TestCleanOperandsMakesRelativePathsAbsolute(t *testing.T) {
+	dir := t.TempDir()
+	t.Chdir(dir)
+
+	wd, err := absolutePath(".")
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	got, err := cleanOperands([]string{"photos/", "a/../b", "/c//d"})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	want := []string{
+		filepath.Join(wd, "photos"), filepath.Join(wd, "b"), "/c/d",
+	}
+	if !slices.Equal(got, want) {
+		t.Errorf("cleanOperands = %q, want %q", got, want)
+	}
+}
+
 func TestRunReportEscapesPaths(t *testing.T) {
 	dir, recs := recsOnDisk(t, awkwardPairRecs())
 	t.Setenv(databaseEnv, seedDatabase(t, recs))
@@ -195,7 +293,7 @@ func TestReportStdoutFailsWhileReading(t *testing.T) {
 	// Counts the records read, and draws nothing.
 	prog := &progress{now: time.Now}
 
-	_, err = readReport(t.Context(), db, "", failingWriter{},
+	_, err = readReport(t.Context(), db, "", nil, failingWriter{},
 		everyPathExists, prog)
 	if !errors.Is(err, errWriteFailed) ||
 		!strings.HasPrefix(err.Error(), "write stdout: ") {
@@ -292,7 +390,8 @@ func TestReadReportOnTerminal(t *testing.T) {
 		waitingFor: countingRecords,
 	}, terminalWidth, time.Hour, time.Now)
 
-	_, err = readReport(t.Context(), db, "", os.Stderr, everyPathExists, p)
+	_, err = readReport(t.Context(), db, "", nil, os.Stderr,
+		everyPathExists, p)
 
 	p.finish()
 
@@ -514,7 +613,7 @@ func TestReadReportChecksOnlyPossibleDuplicates(t *testing.T) {
 		return true
 	}
 
-	_, err = readReport(t.Context(), db, "", io.Discard, exists, nil)
+	_, err = readReport(t.Context(), db, "", nil, io.Discard, exists, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -548,7 +647,8 @@ func TestReadReportDropsGroupLeftWithOnePath(t *testing.T) {
 
 	exists := func(path string) bool { return path != "/a/gone" }
 
-	report, err := readReport(t.Context(), db, "", io.Discard, exists, nil)
+	report, err := readReport(t.Context(), db, "", nil, io.Discard, exists,
+		nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -581,7 +681,7 @@ func TestReadReportKeepsGroupLeftWithTwoPaths(t *testing.T) {
 
 	var out bytes.Buffer
 
-	report, err := readReport(t.Context(), db, "", &out, exists, nil)
+	report, err := readReport(t.Context(), db, "", nil, &out, exists, nil)
 	if err != nil {
 		t.Fatal(err)
 	}

internal/sfdupes/trees.go

@@ -37,12 +37,14 @@ func treesPhase(name string) string {
 
 // runTrees implements the trees subcommand: it reads every record from
 // the database in path order, reconstructs the directory hierarchy from
-// the record paths, computes a Merkle-style digest per directory, and
-// prints maximal duplicate-tree groups as TSV on stdout. Of the scanned
-// filesystem it only checks, with pathExists, that the root of each
-// duplicate tree is still there, never the files below it. It names the
-// database on stderr before it opens it. Any database problem,
-// including a missing database, is fatal.
+// the paths of the records at or below the operands in args (of every
+// record when args is empty), computes a Merkle-style digest per
+// directory, and prints maximal duplicate-tree groups as TSV on stdout.
+// Of the scanned filesystem it only checks, with pathExists, that the
+// root of each duplicate tree is still there, never the files below it;
+// it never looks up an operand. It names the database on stderr before
+// it opens it. Any database problem, including a missing database, is
+// fatal.
 //
 // The work runs in four phases, each under a progress display of its
 // own on stderr: open (open the database), read (read the number of
@@ -50,7 +52,12 @@ func treesPhase(name string) string {
 // hierarchy), group (group the directories by digest) and write (write
 // the groups to stdout). Each display ends before the next phase
 // starts, and before an error is returned to be printed.
-func runTrees(ctx context.Context, stdout io.Writer) error {
+func runTrees(ctx context.Context, args []string, stdout io.Writer) error {
+	operands, err := cleanOperands(args)
+	if err != nil {
+		return err
+	}
+
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
@@ -79,7 +86,7 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 		label: treesPhase("read"), unit: "records", total: -1,
 		waitingFor: countingRecords, stalledOn: "db",
 	})
-	records, super, allDirs, err := readTree(ctx, db, prog)
+	records, super, allDirs, err := readTree(ctx, db, operands, prog)
 
 	prog.finish()
 
@@ -118,10 +125,17 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 }
 
 // readTree gives prog the number of records in db as its total, then
-// reads every record in path order into the directory hierarchy,
-// counting each on prog. It returns the number of records read, the
-// super-root and every directory.
-func readTree(ctx context.Context, db *sql.DB,
+// reads every record in path order, counting each on prog. It adds the
+// records that underOperand finds under operands to the directory
+// hierarchy. It returns the number of records read, the super-root and
+// every directory at or below one of operands.
+//
+// Any other directory lies above an operand and can hold files that are
+// not used, so its digest does not describe it. It is left out of the
+// directories returned. A directory whose parent is left out gets the
+// super-root as its parent, so suppressed never judges its group by
+// that parent's digest.
+func readTree(ctx context.Context, db *sql.DB, operands []string,
 	prog *progress,
 ) (int, *treeNode, []*treeNode, error) {
 	records := 0
@@ -131,7 +145,10 @@ func readTree(ctx context.Context, db *sql.DB,
 		records++
 
 		prog.increment()
-		tree.add(r)
+
+		if underOperand(r.path, operands) {
+			tree.add(r)
+		}
 	})
 	if err != nil {
 		return 0, nil, nil, err
@@ -139,7 +156,21 @@ func readTree(ctx context.Context, db *sql.DB,
 
 	super, allDirs := tree.finish()
 
-	return records, super, allDirs, nil
+	dirs := allDirs[:0]
+
+	for _, d := range allDirs {
+		if !underOperand(d.path, operands) {
+			continue
+		}
+
+		if !underOperand(d.parent.path, operands) {
+			d.parent = super
+		}
+
+		dirs = append(dirs, d)
+	}
+
+	return records, super, dirs, nil
 }
 
 // writeTreeGroups writes dupes to stdout as TSV, a header line and then

internal/sfdupes/trees_test.go

@@ -214,6 +214,57 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 	}
 }
 
+// TestRunTreesOperands runs trees with operands on records in a new
+// directory. x/a and y/a are copies, and so are y/a and srv/b. x and y
+// also hold files that differ. Given x/a and y/a, trees reads x and y
+// as holding one copy each of a, yet neither is reported: only the
+// directories at or below an operand are.
+func TestRunTreesOperands(t *testing.T) {
+	f, g, k := testHash("f"), testHash("g"), testHash("k")
+	dir, recs := recsOnDisk(t, []scanRec{
+		{size: 10, head: f, tail: f, content: f, path: "/srv/b/f"},
+		{size: 10, head: f, tail: f, content: f, path: "/x/a/f"},
+		{size: 20, head: g, tail: g, content: g, path: "/x/g"},
+		{size: 10, head: f, tail: f, content: f, path: "/y/a/f"},
+		{size: 30, head: k, tail: k, content: k, path: "/y/k"},
+	})
+	b, xa, ya := dir+"/srv/b", dir+"/x/a", dir+"/y/a"
+
+	header := "first\tdupe\tfiles\tsize\tdisk_size\n"
+	row := func(first, dupe string) string {
+		return first + "\t" + dupe + "\t1\t10\t0\n"
+	}
+
+	cases := map[string]struct {
+		operands []string
+		want     string
+	}{
+		"none":       {nil, header + row(b, xa) + row(b, ya)},
+		"two copies": {[]string{xa, ya}, header + row(xa, ya)},
+		"parents":    {[]string{dir + "/x", dir + "/y"}, header + row(xa, ya)},
+		"one copy":   {[]string{b}, header},
+	}
+
+	for name, tc := range cases {
+		t.Run(name, func(t *testing.T) {
+			t.Setenv(databaseEnv, seedDatabase(t, recs))
+
+			var stdout, stderr bytes.Buffer
+
+			code := run(append([]string{cmdTrees}, tc.operands...),
+				&stdout, &stderr)
+			if code != exitOK {
+				t.Fatalf("run(trees %q) = %d, want %d; stderr: %s",
+					tc.operands, code, exitOK, stderr.String())
+			}
+
+			if got := stdout.String(); got != tc.want {
+				t.Errorf("stdout = %q, want %q", got, tc.want)
+			}
+		})
+	}
+}
+
 // TestRunTreesDiskSize runs trees on two copies of a tree whose files
 // take different space on disk. The row's disk_size is the sum over the
 // dupe copy's files, those in its subdirectory included.