From 97a02da8370b3fe5c6312a1637b45cb9e9c8ca24 Mon Sep 17 00:00:00 2001 From: sneak Date: Wed, 11 Nov 2026 04:01:34 +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. With operands, trees reports only directories at or below an operand: a directory above them holds 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 | 67 ++++++++++++++++------ TODO.md | 5 ++ internal/sfdupes/cli.go | 27 ++++++--- internal/sfdupes/cli_test.go | 16 +++--- internal/sfdupes/dwim.go | 2 +- internal/sfdupes/report.go | 74 +++++++++++++++++++++---- internal/sfdupes/report_test.go | 98 ++++++++++++++++++++++++++++++++- internal/sfdupes/trees.go | 50 +++++++++++++---- internal/sfdupes/trees_test.go | 49 +++++++++++++++++ 9 files changed, 330 insertions(+), 58 deletions(-) diff --git a/README.md b/README.md index 93e057a..cfeb97a 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. @@ -253,8 +255,8 @@ In order: ``` sfdupes scan [--workers N] [-x] [--no-default-excludes] PATH... -sfdupes report > dupes.tsv -sfdupes trees > dupetrees.tsv +sfdupes report [PATH...] > dupes.tsv +sfdupes trees [PATH...] > dupetrees.tsv sfdupes info sfdupes dwim sfdupes --version @@ -653,12 +655,12 @@ 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 touches the scanned filesystem. It -neither stats nor opens any path in the records. It reads the database and -writes to stdout and stderr, and nothing else. Its output is the same whether or -not the scanned filesystem is still mounted. +`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 "Report paths"). `report` never touches the +scanned filesystem. It neither stats nor opens any path in the records. It reads +the database and writes to stdout and stderr, and nothing else. Its output is +the same whether or not the scanned filesystem is still mounted. Processing: @@ -681,6 +683,26 @@ 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. +#### Report paths + +`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"), so an operand that passes through a symlink matches no record. +- An operand that matches no record is not an error. The report then has no + rows. + #### Report output format The report is TSV (tab-separated values) on stdout. It holds a header line, then @@ -708,7 +730,8 @@ 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. @@ -719,11 +742,12 @@ 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. Like `report`, it never touches the scanned filesystem. It -rebuilds the directory tree from the paths in the records, split on `/`. +`trees` reads the same database as `report` and takes the same `PATH` operands +(see "Report paths"). 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. Like `report`, it never +touches the scanned filesystem. It rebuilds the directory tree from the paths in +the records, split on `/`. Definitions: @@ -750,6 +774,10 @@ 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. A directory above every operand holds + 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. - Within a group, paths are sorted in byte order. The first is `first`, and every other path is a `dupe`. - Groups are ordered by total tree size, largest first, then by `first` path. @@ -799,7 +827,8 @@ 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. @@ -812,7 +841,9 @@ trees: 14 records read, 1 duplicate tree groups, 1 dupe trees, 3.0 KiB reclaimab `dwim`, short for "do what I mean", scans a new machine and reports its duplicate trees in one command. It takes no positional arguments and no flags of -its own. Like `scan`, it should run as root, so that it can read every file. +its own. 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` runs what `sfdupes scan /` runs with no flags. The walk skips the default excludes and crosses into other filesystems. `--workers` keeps its default. The @@ -1198,7 +1229,7 @@ showing the count it stopped at. `--workers abc`; - `scan` with no operand; - `--workers` below 1; - - `report`, `trees`, `info` or `dwim` with a positional argument. + - `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/TODO.md b/TODO.md index e0cee09..6d4d630 100644 --- a/TODO.md +++ b/TODO.md @@ -29,6 +29,11 @@ Newest first. An entry ends with its date and its issue or branch, where those are known. +- `report` and `trees` take optional `PATH` operands. With operands, they use + only the records at or below them. `trees` then reports only directories at or + below an operand. Operands are made absolute and cleaned as text, never looked + up on the filesystem (2026-11-11, + https://git.eeqj.de/sneak/sfdupes/issues/174) - `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, diff --git a/internal/sfdupes/cli.go b/internal/sfdupes/cli.go index bc0539f..7cb253e 100644 --- a/internal/sfdupes/cli.go +++ b/internal/sfdupes/cli.go @@ -31,6 +31,13 @@ const ( cmdDwim = "dwim" ) +// reportPathsHelp explains the PATH operands of report and trees in +// their help. +const reportPathsHelp = "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. @@ -161,20 +168,24 @@ 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" + reportPathsHelp, + 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" + reportPathsHelp, + Args: cobra.ArbitraryArgs, + RunE: runE(func(ctx context.Context, args []string) error { + return runTrees(ctx, args, stdout) }), } diff --git a/internal/sfdupes/cli_test.go b/internal/sfdupes/cli_test.go index 6e65e7f..71be522 100644 --- a/internal/sfdupes/cli_test.go +++ b/internal/sfdupes/cli_test.go @@ -576,14 +576,14 @@ 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", @@ -619,8 +619,6 @@ 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}, @@ -1726,9 +1724,13 @@ 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 5158a46..0a06f58 100644 --- a/internal/sfdupes/dwim.go +++ b/internal/sfdupes/dwim.go @@ -25,7 +25,7 @@ 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 } diff --git a/internal/sfdupes/report.go b/internal/sfdupes/report.go index 949b38a..0cdc9a7 100644 --- a/internal/sfdupes/report.go +++ b/internal/sfdupes/report.go @@ -7,6 +7,7 @@ import ( "fmt" "io" "os" + "path/filepath" "slices" "strings" "time" @@ -41,10 +42,11 @@ func reportPhase(name string) string { } // runReport implements the report subcommand: it prints the file-level -// duplicates report as TSV on stdout. It never touches the scanned -// filesystem; its only I/O is the database, stdout, and stderr. 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 +// given paths, or from every record when none is given. It never +// touches the scanned filesystem; its only I/O is the database, +// stdout, and stderr. 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 @@ -52,7 +54,12 @@ 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 { + paths, err := reportPaths(args) + if err != nil { + return err + } + dbPath, source, err := databasePath() if err != nil { return err @@ -83,7 +90,7 @@ func runReport(ctx context.Context, stdout io.Writer) error { label: reportPhase("read"), unit: "records", total: -1, waitingFor: countingRecords, stalledOn: "db/out", }) - report, err := readReport(ctx, db, dbPath, stdout, prog) + report, err := readReport(ctx, db, dbPath, paths, stdout, prog) prog.finish() @@ -104,11 +111,12 @@ 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. stdout may be the terminal prog is drawn on, so the lines go +// read. Only the records that inReportPaths selects from paths join a +// 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, prog *progress, + paths []string, stdout io.Writer, prog *progress, ) (*reportWriter, error) { out := prog.writer(stdout) report := &reportWriter{out: out} @@ -123,6 +131,12 @@ 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 !inReportPaths(r.path, paths) { + return nil + } + writeErr = report.add(r) return writeErr @@ -154,7 +168,7 @@ 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 @@ -170,8 +184,6 @@ 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) @@ -246,6 +258,46 @@ func (w *reportWriter) finish() error { return w.writeGroups() } +// reportPaths returns the paths given to 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 a given path is cleaned to match them. No path is looked up +// on the filesystem. +func reportPaths(args []string) ([]string, error) { + paths := 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) + } + + paths = append(paths, filepath.Clean(abs)) + } + + return paths, nil +} + +// inReportPaths reports whether path is one of paths or lies below one +// of them. Each of paths is clean and absolute, as reportPaths returns +// it. With no paths, a report covers the whole database, so every path +// is in it. +func inReportPaths(path string, paths []string) bool { + if len(paths) == 0 { + return true + } + + for _, p := range paths { + // Only the root directory's clean path ends in "/". + dir := strings.TrimSuffix(p, "/") + "/" + if path == p || 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 5aff75b..4e357d7 100644 --- a/internal/sfdupes/report_test.go +++ b/internal/sfdupes/report_test.go @@ -80,7 +80,7 @@ func dupeGroups(t *testing.T, db *sql.DB) []dupeGroup { var out bytes.Buffer - _, err := readReport(t.Context(), db, "", &out, nil) + _, err := readReport(t.Context(), db, "", nil, &out, nil) if err != nil { t.Fatal(err) } @@ -126,6 +126,98 @@ func dupeGroupsOf(t *testing.T, recs []scanRec) []dupeGroup { return dupeGroups(t, db) } +// TestRunReportPaths runs report with paths on three copies of one +// file, two of them under /srv/photos, and a fourth copy in +// /srv/photos2. Only the records at or below the given paths form the +// groups and the totals, however each path is written. +// +//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr +func TestRunReportPaths(t *testing.T) { + h := testHash("h") + a, x, y, z := "/a/copy", "/srv/photos/x", "/srv/photos/y", "/srv/photos2/z" + + recs := make([]scanRec, 0, 4) + for _, p := range []string{a, x, y, z} { + recs = append(recs, + scanRec{size: 7, head: h, tail: h, content: h, path: p}) + } + + 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 { + paths []string + want string + summary string + }{ + "directory": {[]string{"/srv/photos"}, photos, + "1 duplicate groups, 1 dupe files, 7 B reclaimable"}, + "trailing slash": {[]string{"/srv/photos/"}, photos, ""}, + "dot and dot-dot": {[]string{"/srv/./a/../photos"}, photos, ""}, + "files": {[]string{a, z}, header + row(a, z), ""}, + "overlapping": {[]string{"/srv", "/srv/photos"}, + header + row(x, y) + row(x, z), ""}, + "root": {[]string{"/"}, + header + row(a, x) + row(a, y) + row(a, z), ""}, + "no record": {[]string{"/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.paths...), + &stdout, os.Stderr) + if code != exitOK { + t.Fatalf("run(report %q) = %d, want %d; stderr: %s", + tc.paths, 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 paths. + 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 TestReportPathsMakesRelativePathsAbsolute(t *testing.T) { + dir := t.TempDir() + t.Chdir(dir) + + wd, err := absolutePath(".") + if err != nil { + t.Fatal(err) + } + + got, err := reportPaths([]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("reportPaths = %q, want %q", got, want) + } +} + func TestRunReportEscapesPaths(t *testing.T) { t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs())) @@ -172,7 +264,7 @@ func TestReportStdoutFailsWhileReading(t *testing.T) { // Counts the records read, and draws nothing. prog := &progress{now: time.Now} - _, err = readReport(t.Context(), db, "", failingWriter{}, prog) + _, err = readReport(t.Context(), db, "", nil, failingWriter{}, prog) if !errors.Is(err, errWriteFailed) || !strings.HasPrefix(err.Error(), "write stdout: ") { t.Errorf("error = %v, want write stdout: %v", err, errWriteFailed) @@ -266,7 +358,7 @@ func TestReadReportOnTerminal(t *testing.T) { waitingFor: countingRecords, }, terminalWidth, time.Hour, time.Now) - _, err = readReport(t.Context(), db, "", os.Stderr, p) + _, err = readReport(t.Context(), db, "", nil, os.Stderr, p) p.finish() diff --git a/internal/sfdupes/trees.go b/internal/sfdupes/trees.go index 873da23..2f58fd2 100644 --- a/internal/sfdupes/trees.go +++ b/internal/sfdupes/trees.go @@ -37,8 +37,9 @@ 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. It never +// the paths of the records at or below the given paths (of every record +// when none is given), computes a Merkle-style digest per directory, +// and prints maximal duplicate-tree groups as TSV on stdout. It never // touches the scanned filesystem; its only I/O is the database, stdout, // and stderr. It names the database on stderr before it opens it. Any // database problem, including a missing database, is fatal. @@ -49,7 +50,12 @@ 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 { + paths, err := reportPaths(args) + if err != nil { + return err + } + dbPath, source, err := databasePath() if err != nil { return err @@ -78,7 +84,7 @@ 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, paths, prog) prog.finish() @@ -117,10 +123,17 @@ 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 inReportPaths selects from paths to the directory +// hierarchy. It returns the number of records read, the super-root and +// every directory at or below one of paths. +// +// A directory above every one of paths holds only the selected records +// under it, 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, paths []string, prog *progress, ) (int, *treeNode, []*treeNode, error) { records := 0 @@ -130,7 +143,10 @@ func readTree(ctx context.Context, db *sql.DB, records++ prog.increment() - tree.add(r) + + if inReportPaths(r.path, paths) { + tree.add(r) + } }) if err != nil { return 0, nil, nil, err @@ -138,7 +154,21 @@ 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 !inReportPaths(d.path, paths) { + continue + } + + if !inReportPaths(d.parent.path, paths) { + 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 356d48b..cf50a57 100644 --- a/internal/sfdupes/trees_test.go +++ b/internal/sfdupes/trees_test.go @@ -212,6 +212,55 @@ func TestRunTreesEscapesPaths(t *testing.T) { } } +// TestRunTreesPaths runs trees with paths. /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 a +// given path are. +func TestRunTreesPaths(t *testing.T) { + f, g, k := testHash("f"), testHash("g"), testHash("k") + recs := []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"}, + } + + header := "first\tdupe\tfiles\tsize\tdisk_size\n" + + cases := map[string]struct { + paths []string + want string + }{ + "none": {nil, header + "/srv/b\t/x/a\t1\t10\t0\n" + + "/srv/b\t/y/a\t1\t10\t0\n"}, + "two copies": {[]string{"/x/a", "/y/a"}, + header + "/x/a\t/y/a\t1\t10\t0\n"}, + "parents": {[]string{"/x", "/y"}, header + "/x/a\t/y/a\t1\t10\t0\n"}, + "one copy": {[]string{"/srv/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.paths...), + &stdout, &stderr) + if code != exitOK { + t.Fatalf("run(trees %q) = %d, want %d; stderr: %s", + tc.paths, 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.