From 729518c480c8483bdb38ce920864e58d1f833477 Mon Sep 17 00:00:00 2001 From: sneak Date: Wed, 11 Nov 2026 07:00:03 +0000 Subject: [PATCH] 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. An empty operand is a usage error, as --exclude "" is, since it would name the working directory. 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 --- README.md | 71 ++++++++++++---- internal/sfdupes/cli.go | 44 +++++++--- internal/sfdupes/cli_test.go | 31 ++++--- internal/sfdupes/dwim.go | 2 +- internal/sfdupes/report.go | 84 +++++++++++++++--- internal/sfdupes/report_test.go | 145 ++++++++++++++++++++++++++++++-- internal/sfdupes/trees.go | 59 ++++++++++--- internal/sfdupes/trees_test.go | 51 +++++++++++ 8 files changed, 412 insertions(+), 75 deletions(-) diff --git a/README.md b/README.md index 0a36a64..84599cf 100644 --- a/README.md +++ b/README.md @@ -43,7 +43,9 @@ as opposed to a directory, a symlink or a device node. A symlink is a file that holds the path of another file and stands in for it. A device node is a file 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. +Both cover the whole database, or only the paths given after them, as in +`sfdupes report /srv/photos`. `info` prints the database's path, size and record +count. The database is `/var/lib/sfdupes/db.sqlite` unless `SFDUPES_DATABASE` names another file. The first `scan` creates it. @@ -258,8 +260,8 @@ In order: ``` sfdupes scan [--workers N] [-x] [--no-default-excludes] [--exclude PATH]... PATH... -sfdupes report > dupes.tsv -sfdupes trees > dupetrees.tsv +sfdupes report [PATH...] > dupes.tsv +sfdupes trees [PATH...] > dupetrees.tsv sfdupes info sfdupes dwim [--workers N] [-x] [--no-default-excludes] [--exclude PATH]... sfdupes --version @@ -686,11 +688,12 @@ and `scan` leaves it ignored. ### `report` mode -`report` reads every record from the database. It takes no positional arguments. -A positional argument is anything on the command line that is not a flag, such -as the paths `scan` takes. `report` never opens a scanned file. It checks that -each path in a group still exists, and looks at no other path. The check is -`lstat`, the system call that looks up a path without following a symlink: +`report` reads every record from the database. It takes optional `PATH` +operands. With none, it uses every record. With one or more, it uses only the +records at or below them (see "Operands of `report` and `trees`"). `report` +never opens a scanned file. It checks that each path in a group still exists, +and looks at no other path. It never looks up an operand. The check is `lstat`, +the system call that looks up a path without following a symlink: - A path is gone when `lstat` finds that it, or a directory above it, does not exist. @@ -722,6 +725,27 @@ with one signature come together, and so do the records of one size. So `report` holds only the duplicate groups of the size it is reading. Once it reaches a smaller size, it writes them, ordered by `first` path. +#### Operands of `report` and `trees` + +`report` and `trees` take the same `PATH` operands: + +- A record is used when its path is an operand or lies below one. `/srv/photos` + covers `/srv/photos/x` but not `/srv/photos2/x`. +- The records used are grouped, ordered and totalled as they are without + operands. A copy outside the operands is not reported. With copies `/a/f`, + `/srv/photos/x` and `/srv/photos/y`, `sfdupes report /srv/photos` prints one + row, `/srv/photos/x` and `/srv/photos/y`. +- A relative operand is joined to the working directory as `pwd -P` prints it. +- Each operand is then cleaned as text, as `realpath -ms` prints it. Its `.` + elements and repeated or trailing slashes are dropped. Each `..` drops the + element before it. +- No operand is looked up on the filesystem. A symlink in an operand is not + followed, and an operand need not exist. The records hold real paths (see + "Operands" under "`scan` mode"), so an operand that passes through a symlink + matches no record. +- An operand that matches no record is not an error; it adds nothing to the + report. + #### Report output format The report is TSV (tab-separated values) on stdout. It holds a header line, then @@ -749,7 +773,8 @@ Grouping and ordering use the stored path. The warnings about skipped paths that The summary line on stderr gives: -- the records read; +- the records read, which are all the records in the database, with or without + operands; - the duplicate groups; - the dupe files, which is the number of rows; - the reclaimable bytes, the sum of `size` over all rows. @@ -760,11 +785,12 @@ report: 14 records read, 4 duplicate groups, 7 dupe files, 10.0 KiB reclaimable ### `trees` mode -`trees` reads the same database as `report` and takes no positional arguments. -It reports whole duplicate directory trees. Two directories are duplicate trees -when they hold the same relative paths, and each path holds a file with the same -signature in both. It rebuilds the directory tree from the paths in the records, -split on `/`. Like `report`, it never opens a scanned file. It checks only that +`trees` reads the same database as `report` and takes the same `PATH` operands +(see "Operands of `report` and `trees`"). It reports whole duplicate directory +trees. Two directories are duplicate trees when they hold the same relative +paths, and each path holds a file with the same signature in both. It rebuilds +the directory tree from the paths in the records, split on `/`. Like `report`, +it never opens a scanned file and never looks up an operand. It checks only that the directory at the top of each copy still exists, as `report` checks a path. Definitions: @@ -792,6 +818,11 @@ Processing: directories that all have the same digest. The parents' group, or an ancestor's, already implies it. A group is always reported when it holds sibling directories, or when its members' parents have different digests. +- With operands, `trees` builds the tree from the records it uses. It reports + only directories at or below an operand. Any other directory lies above an + operand and can hold files that are not used, so its digest does not describe + it. Such a directory is never reported and never implies a group of its + children. - A directory that is gone is dropped from its group. A group left with fewer than two directories is not reported. - Within a group, paths are sorted in byte order. The first is `first`, and @@ -845,7 +876,8 @@ directory's path is `/`. The summary line on stderr gives: -- the records read; +- the records read, which are all the records in the database, with or without + operands; - the duplicate-tree groups; - the dupe trees, which is the number of rows; - the reclaimable bytes, the sum of `size` over all rows. @@ -857,8 +889,10 @@ trees: 14 records read, 1 duplicate tree groups, 1 dupe trees, 3.0 KiB reclaimab ### `dwim` mode `dwim`, short for "do what I mean", scans a new machine and reports its -duplicate trees in one command. It takes no positional arguments. Like `scan`, -it should run as root, so that it can read every file. +duplicate trees in one command. It takes no positional arguments. A positional +argument is anything on the command line that is not a flag, such as the paths +`scan` takes. Like `scan`, it should run as root, so that it can read every +file. `dwim` takes these flags of `scan`, with the same meaning (see "Settings"): @@ -1260,7 +1294,8 @@ showing the count it stopped at. - `scan` with no operand; - `--workers` below 1; - an empty `--exclude` value, as in `--exclude ""`; - - `report`, `trees`, `info` or `dwim` with a positional argument. + - an empty `PATH` for `report` or `trees`, as in `sfdupes report ""`; + - `info` or `dwim` with a positional argument. A fatal error is reported on stderr, starting with `sfdupes:`. A failed write to stdout, such as a full disk, is reported the same way. Two cases never reach diff --git a/internal/sfdupes/cli.go b/internal/sfdupes/cli.go index aa36782..ed4f566 100644 --- a/internal/sfdupes/cli.go +++ b/internal/sfdupes/cli.go @@ -49,6 +49,13 @@ const escapesHelp = `Four characters in a path are escaped, so each row stays on \r a carriage return ` +// operandsHelp is the paragraph of the report and trees help on their +// PATH operands (README "Operands of `report` and `trees`"). +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. +` + // reportHelp, treesHelp, infoHelp and dwimHelp follow the one-line // summary in the help of their subcommands. const ( @@ -61,7 +68,7 @@ row per duplicate file. The columns are: Rows are ordered by size, largest first, then by path. -` + escapesHelp +` + escapesHelp + "\n" + operandsHelp treesHelp = `The report is tab-separated text on stdout: a header line, then one row per duplicate directory tree. The columns are: @@ -74,7 +81,7 @@ row per duplicate directory tree. The columns are: Rows are ordered by size, largest first, then by path. -` + escapesHelp +` + escapesHelp + "\n" + operandsHelp infoHelp = `The details go to stdout, one per line. Each line holds a name and its value, separated by a tab: @@ -108,6 +115,11 @@ var errWorkersBelowOne = errors.New("--workers must be at least 1") // would name the working directory. var errEmptyExcludeValue = errors.New("--exclude must not be empty") +// errEmptyOperand is the usage error for an empty PATH operand of +// report or trees, as from "$DIR" with DIR unset. Taken as a path, it +// would name the working directory. +var errEmptyOperand = errors.New("PATH must not be empty") + // Version is the build version, injected at link time via -ldflags // (see the Makefile); empty when the linker set none, as for a binary // built by go install. buildVersion turns it into what --version prints. @@ -229,20 +241,20 @@ 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) + Args: rejectEmptyOperand, + 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) + Args: rejectEmptyOperand, + RunE: runE(func(ctx context.Context, args []string) error { + return runTrees(ctx, args, stdout) }), } @@ -387,6 +399,18 @@ func rejectEmptyExcludeValue(cmd *cobra.Command, excludePaths []string) error { return errEmptyExcludeValue } +// rejectEmptyOperand rejects an empty PATH operand of report or trees. +// That is a usage error reported in one line, as for --workers below 1. +func rejectEmptyOperand(cmd *cobra.Command, args []string) error { + if !slices.Contains(args, "") { + return nil + } + + cmd.SilenceUsage = true + + return errEmptyOperand +} + // runE adapts a subcommand implementation, or the version print, to // cobra's RunE. Cobra prints the error and the command's usage text for // every error RunE returns, but a subcommand that ran and failed has no diff --git a/internal/sfdupes/cli_test.go b/internal/sfdupes/cli_test.go index bc9b84d..5c10bd8 100644 --- a/internal/sfdupes/cli_test.go +++ b/internal/sfdupes/cli_test.go @@ -583,14 +583,14 @@ 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", @@ -626,8 +626,6 @@ 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}, @@ -764,11 +762,16 @@ func TestRunHelpDescribesDatabaseAndOutput(t *testing.T) { t.Parallel() // README §Settings: the help names the database, and says what - // report, trees, info and dwim print. + // report, trees, info and dwim print. The help of report and trees + // also explains their PATH operands. database := []string{ "scan and dwim store", databaseEnv, defaultDatabasePath, "needs root", } escapes := []string{`\\`, `\t`, `\n`, `\r`} + operands := []string{ + "With PATH operands", "at or below them", "working directory", + "No PATH is looked up", "not followed", + } // The subcommand whose help is printed; none for the root. cases := []struct { @@ -779,17 +782,17 @@ func TestRunHelpDescribesDatabaseAndOutput(t *testing.T) { {[]string{cmdScan}, database}, { []string{cmdReport}, - append([]string{ + slices.Concat([]string{ "tab-separated", "\n first ", "\n dupe ", "\n size ", "largest first", - }, escapes...), + }, escapes, operands), }, { []string{cmdTrees}, - append([]string{ + slices.Concat([]string{ "tab-separated", "\n first ", "\n dupe ", "\n files ", "\n size ", "\n disk_size ", "largest first", - }, escapes...), + }, escapes, operands), }, { []string{cmdInfo}, @@ -1839,9 +1842,13 @@ 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 { diff --git a/internal/sfdupes/dwim.go b/internal/sfdupes/dwim.go index c365408..cd8fcdd 100644 --- a/internal/sfdupes/dwim.go +++ b/internal/sfdupes/dwim.go @@ -26,7 +26,7 @@ func runDwim( return err } - err = runTrees(ctx, stdout) + err = runTrees(ctx, nil, stdout) if err != nil { return err } diff --git a/internal/sfdupes/report.go b/internal/sfdupes/report.go index 84eb53f..543b2bd 100644 --- a/internal/sfdupes/report.go +++ b/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 +288,47 @@ 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. None is empty: rejectEmptyOperand refuses an +// empty operand on the command line. +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. diff --git a/internal/sfdupes/report_test.go b/internal/sfdupes/report_test.go index e976688..7d120e8 100644 --- a/internal/sfdupes/report_test.go +++ b/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 +149,136 @@ 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) + } +} + +// TestRunReportsRejectEmptyOperand checks that an empty PATH operand of +// report or trees, alone or after another operand, is a usage error +// reported in one line before the database is opened (README "Error +// handling and exit codes"). +func TestRunReportsRejectEmptyOperand(t *testing.T) { + cases := map[string][]string{ + "report": {cmdReport, ""}, + "trees": {cmdTrees, ""}, + "after an operand": {cmdTrees, t.TempDir(), ""}, + } + + for name, args := range cases { + t.Run(name, func(t *testing.T) { + // No database exists there, so opening one would be a fatal + // error, exit 1. + t.Setenv(databaseEnv, testDBPath(t)) + + var stdout, stderr bytes.Buffer + + code := run(args, &stdout, &stderr) + if code != exitUsage { + t.Errorf("run(%q) = %d, want %d", args, code, exitUsage) + } + + want := "Error: PATH must not be empty\n" + if stdout.String() != "" || stderr.String() != want { + t.Errorf("stdout, stderr = %q, %q, want \"\", %q", + stdout.String(), stderr.String(), want) + } + }) + } +} + func TestRunReportEscapesPaths(t *testing.T) { dir, recs := recsOnDisk(t, awkwardPairRecs()) t.Setenv(databaseEnv, seedDatabase(t, recs)) @@ -195,7 +326,7 @@ 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 +423,8 @@ 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 +646,7 @@ 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 +680,8 @@ 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 +714,7 @@ 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) } diff --git a/internal/sfdupes/trees.go b/internal/sfdupes/trees.go index 36bfb12..b648a76 100644 --- a/internal/sfdupes/trees.go +++ b/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 diff --git a/internal/sfdupes/trees_test.go b/internal/sfdupes/trees_test.go index 6a4d722..e0221f3 100644 --- a/internal/sfdupes/trees_test.go +++ b/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. -- 2.54.0