Print help that was asked for to stdout (closes #179)

--help, -h and the help subcommand now print to stdout and exit 0, so
the help can be paged and searched. The usage text of a usage error
stays on stderr with exit 2, as does help for an unknown subcommand
("sfdupes help scna"). A failed write of the help exits 1.

Cobra prints help to the command's output writer, which stays stderr,
drops a failed write, and returns no error after help. So run replaces
the help function and the help subcommand: the help goes into a buffer,
then to stdout, and the error sets the exit code.

README "Settings" and goal 4 say so.

Model: opus-5-5

README.md

@@ -253,8 +253,9 @@ In order:
    `trees` check only that each copy they name still exists, and leave out a
    copy that is gone. `scan` is built to run from `cron`. The reports run at any
    time, against what the database holds.
-4. **Keep the streams apart.** Everything on stdout is machine-readable data.
+4. **Keep the streams apart.** stdout holds only what was asked for:
-   Everything for a human reader, such as progress and warnings, goes to stderr.
+   machine-readable data, or help. Everything else for a human reader, such as
+   progress and warnings, goes to stderr.
 
 ### Subcommands
 
@@ -324,12 +325,13 @@ The reference below is also the program's specification.
   "Operands").
 - `--version`, `-v` prints `sfdupes VERSION` (see "Install") to stdout and
   exits 0. It writes nothing to stderr.
-- `--help`, `-h`, alone or after a subcommand, prints the help text to stderr
+- `--help`, `-h`, alone or after a subcommand, prints the help text to stdout
-  and exits 0. It writes nothing to stdout. The help of `sfdupes` and of `scan`
+  and exits 0. It writes nothing to stderr. `sfdupes help` and
-  names the database. The help of `report`, `trees`, `info` and `dwim` says what
+  `sfdupes help COMMAND` do the same. The help of `sfdupes` and of `scan` names
-  each prints. `sfdupes scan --help` and `sfdupes dwim --help` also list the
+  the database. The help of `report`, `trees`, `info` and `dwim` says what each
-  default excludes of the system they run on, and the filesystem types the walk
+  prints. `sfdupes scan --help` and `sfdupes dwim --help` also list the default
-  never records anything on.
+  excludes of the system they run on, and the filesystem types the walk never
+  records anything on.
 
 ### Duplicate detection
 
@@ -563,7 +565,7 @@ walk practical on large or busy storage pools.
     `scan` prints a line on stderr naming the path and its filesystem type:
 
     ```
-    scan: skipped /dev/shm (tmpfs, not a persistent filesystem)
+    scan: left out /dev/shm (tmpfs, not a persistent filesystem)
     ```
 
     The path is not counted as skipped. The records below it are kept, as
@@ -573,7 +575,7 @@ walk practical on large or busy storage pools.
   For each one it reaches, `scan` prints a line on stderr naming it:
 
     ```
-    scan: skipped /srv/cache (--exclude)
+    scan: left out /srv/cache (--exclude)
     ```
 
     The path is not counted as skipped. The scan keeps the records at and below
@@ -622,7 +624,7 @@ walk practical on large or busy storage pools.
     not enter, `scan` prints a line on stderr naming it:
 
     ```
-    scan: skipped /var/tmp (default exclude)
+    scan: left out /var/tmp (default exclude)
     ```
 
     The directory is not counted as skipped. `scan` prints the filesystem line
@@ -682,6 +684,18 @@ scan: 123400 files seen (1200 added, 34 updated, 56 removed, 122166 unchanged),
 
 `removed` counts deleted records, which are not part of the files seen.
 
+The warning for a skipped path names the path once and gives the reason:
+
+```
+scan: skipped /srv/a/closed (permission denied)
+scan: skipped /srv/a/pipe (a FIFO)
+```
+
+The summary counts each path named in such a warning. A line for a path left out
+on purpose starts with `scan: left out` instead, and is not counted. A search of
+the log for `scan: skipped` therefore finds the paths the summary counts. When a
+file with several hard links cannot be read, each of its paths gets a warning.
+
 #### Stopping a scan
 
 `scan` stops cleanly on `SIGINT`, the signal Ctrl-C sends, or `SIGTERM`, the

internal/sfdupes/cli.go

@@ -3,6 +3,7 @@
 package sfdupes
 
 import (
+	"bytes"
 	"context"
 	"errors"
 	"fmt"
@@ -176,9 +177,32 @@ func run(args []string, stdout, stderr io.Writer) int {
 	}
 
 	root := newRootCommand(stdout, stderr)
+
+	// Help that was asked for, with --help, -h or the help subcommand,
+	// goes to stdout. Execute returns no error after help, so helpErr
+	// keeps the one printHelp returns. Cobra's own help subcommand is
+	// replaced because it answers "sfdupes help scna" with the help of
+	// sfdupes.
+	var helpErr error
+
+	cobraHelp := root.HelpFunc()
+	root.SetHelpFunc(func(cmd *cobra.Command, _ []string) {
+		helpErr = printHelp(cmd, cmd.Flags().Args(), cobraHelp, stdout)
+	})
+	root.SetHelpCommand(&cobra.Command{
+		Use:   "help [command]",
+		Short: "Help about any command",
+		Run: func(_ *cobra.Command, names []string) {
+			helpErr = printHelp(root, names, cobraHelp, stdout)
+		},
+	})
+
 	root.SetArgs(args)
 
 	err := root.Execute()
+	if err == nil {
+		err = helpErr
+	}
 
 	var fatal fatalError
 
@@ -195,14 +219,62 @@ func run(args []string, stdout, stderr io.Writer) int {
 
 		return exitFatal
 	default:
-		// A usage error, which cobra has already reported on stderr.
+		// A usage error, which cobra or printHelp has already reported
+		// on stderr.
 		return exitUsage
 	}
 }
 
+// printHelp prints help that was asked for to stdout. It is the help of
+// cmd, or, for a command with subcommands, of the subcommand that
+// operands name: scan in "sfdupes help scan". Operands that name none,
+// as in "sfdupes help scna" or "sfdupes scna --help", are a usage
+// error, reported on stderr as for "sfdupes scna".
+//
+// cobraHelp is cobra's own help function. It prints to the command's
+// output writer, which is stderr, and drops a failed write. So the help
+// goes into a buffer first, and a failed write of the buffer to stdout
+// is a fatal error.
+func printHelp(
+	cmd *cobra.Command, operands []string,
+	cobraHelp func(*cobra.Command, []string), stdout io.Writer,
+) error {
+	if cmd.HasSubCommands() {
+		cmd, operands, _ = cmd.Find(operands)
+	}
+
+	// When the help subcommand runs instead of cmd, cobra has not yet
+	// added the --help flag that cmd's help and usage text list.
+	cmd.InitDefaultHelpFlag()
+
+	// Operands left over here name no subcommand. They are reported as
+	// cobra reports "sfdupes scna", which cobra.NoArgs rejects.
+	if cmd.HasSubCommands() && len(operands) > 0 {
+		err := cobra.NoArgs(cmd, operands)
+		cmd.PrintErrln(cmd.ErrPrefix(), err.Error())
+		cmd.Println(cmd.UsageString())
+
+		return err
+	}
+
+	out := cmd.OutOrStderr()
+	help := new(bytes.Buffer)
+	cmd.SetOut(help)
+	cobraHelp(cmd, nil)
+	cmd.SetOut(out)
+
+	_, err := stdout.Write(help.Bytes())
+	if err != nil {
+		return fatalError{err: fmt.Errorf("write stdout: %w", err)}
+	}
+
+	return nil
+}
+
 // newRootCommand builds the command tree. Everything on stdout is
-// machine-readable data, the version line included; all human-facing
+// machine-readable data, the version line included, or help that was
-// output (help, usage, errors) goes to stderr.
+// asked for, which run prints. The rest of the human-facing output
+// (usage, errors) goes to stderr.
 func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 	var showVersion bool
 
@@ -235,11 +307,13 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 			return errNoSubcommand
 		},
 	}
+	// Cobra prints the usage text of a usage error to the command's
+	// output writer, so that writer is stderr.
 	root.SetOut(stderr)
 	root.SetErr(stderr)
 	root.CompletionOptions.DisableDefaultCmd = true
 
-	// Cobra's built-in version flag prints through the help writer,
+	// Cobra's built-in version flag prints to the output writer,
 	// stderr; this one prints to stdout.
 	root.Flags().BoolVarP(&showVersion, "version", "v", false,
 		"print the version to stdout")

internal/sfdupes/cli_test.go

@@ -26,6 +26,9 @@ const usageMarker = "Usage:"
 // helpFlag asks for the help text.
 const helpFlag = "--help"
 
+// helpCommand is the subcommand that prints the help text.
+const helpCommand = "help"
+
 // workersFlag is the scan and dwim flag that sets the worker count.
 const workersFlag = "--workers"
 
@@ -625,6 +628,14 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 
 func TestRunUsageErrors(t *testing.T) {
 	// Usage errors keep exiting 2 with cobra's own report on stderr.
+	// An unknown subcommand is reported the same way with or without a
+	// request for help: the line naming it, then the usage text.
+	const (
+		unknown       = "nope"
+		unknownReport = "unknown command \"" + unknown +
+			"\" for \"sfdupes\"\n" + usageMarker
+	)
+
 	cases := map[string]struct {
 		args []string
 		want string
@@ -634,7 +645,13 @@ func TestRunUsageErrors(t *testing.T) {
 		"info with args":     {[]string{cmdInfo, "x"}, usageMarker},
 		"dwim with args":     {[]string{cmdDwim, "x"}, usageMarker},
 		"unknown flag":       {[]string{cmdScan, "--nope", "/"}, usageMarker},
-		"unknown subcommand": {[]string{"nope"}, "unknown command"},
+		"unknown subcommand": {[]string{unknown}, unknownReport},
+		"unknown subcommand with --help": {
+			[]string{unknown, helpFlag}, unknownReport,
+		},
+		"help for an unknown subcommand": {
+			[]string{helpCommand, unknown}, unknownReport,
+		},
 	}
 
 	for name, tc := range cases {
@@ -700,9 +717,12 @@ func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
 func TestRunHelp(t *testing.T) {
 	t.Parallel()
 
-	// README §Settings: help goes to stderr, exits 0, and leaves stdout
+	// README §Settings: help goes to stdout, exits 0, and leaves stderr
 	// empty.
-	cases := [][]string{{helpFlag}, {"-h"}, {cmdScan, helpFlag}}
+	cases := [][]string{
+		{helpFlag}, {"-h"}, {helpCommand},
+		{cmdScan, helpFlag}, {helpCommand, cmdScan},
+	}
 
 	for _, args := range cases {
 		var stdout, stderr bytes.Buffer
@@ -712,14 +732,20 @@ func TestRunHelp(t *testing.T) {
 			t.Errorf("run(%v) = %d, want %d", args, code, exitOK)
 		}
 
-		if !strings.Contains(stderr.String(), usageMarker) {
+		if !strings.Contains(stdout.String(), usageMarker) {
-			t.Errorf("run(%v) stderr = %q, want the help text",
+			t.Errorf("run(%v) stdout = %q, want the help text",
-				args, stderr.String())
+				args, stdout.String())
 		}
 
-		if got := stdout.String(); got != "" {
+		// The help subcommand prints the same help as --help, which
-			t.Errorf("run(%v) stdout = %q, want nothing (data only)",
+		// lists --help itself.
-				args, got)
+		if !strings.Contains(stdout.String(), "-h, "+helpFlag) {
+			t.Errorf("run(%v) stdout = %q, want it to list %s",
+				args, stdout.String(), helpFlag)
+		}
+
+		if got := stderr.String(); got != "" {
+			t.Errorf("run(%v) stderr = %q, want nothing", args, got)
 		}
 
 		// README §Location: the help of sfdupes and of scan says where
@@ -729,9 +755,9 @@ func TestRunHelp(t *testing.T) {
 			"scan and dwim store", databaseEnv, rootDatabasePath,
 			stateHomeEnv, "~/.local/state", "not an absolute path is an error",
 		} {
-			if !strings.Contains(stderr.String(), want) {
+			if !strings.Contains(stdout.String(), want) {
-				t.Errorf("run(%v) stderr = %q, want it to name %q",
+				t.Errorf("run(%v) stdout = %q, want it to name %q",
-					args, stderr.String(), want)
+					args, stdout.String(), want)
 			}
 		}
 	}
@@ -741,17 +767,48 @@ func TestRunHelp(t *testing.T) {
 
 	run([]string{cmdScan, "-h"}, &stdout, &stderr)
 
-	if !strings.Contains(stderr.String(), excludeFlag+" PATH") {
+	if !strings.Contains(stdout.String(), excludeFlag+" PATH") {
-		t.Errorf("scan -h stderr = %q, want %s PATH", stderr.String(),
+		t.Errorf("scan -h stdout = %q, want %s PATH", stdout.String(),
 			excludeFlag)
 	}
 }
 
+func TestRunHelpScanPrintsScanHelp(t *testing.T) {
+	t.Parallel()
+
+	// "sfdupes help scan" and "sfdupes --help scan" print exactly what
+	// "sfdupes scan --help" prints: the help of scan, not of sfdupes.
+	var want bytes.Buffer
+
+	run([]string{cmdScan, helpFlag}, &want, io.Discard)
+
+	for _, args := range [][]string{
+		{helpCommand, cmdScan}, {helpFlag, cmdScan},
+	} {
+		var stdout, stderr bytes.Buffer
+
+		code := run(args, &stdout, &stderr)
+		if code != exitOK {
+			t.Errorf("run(%v) = %d, want %d", args, code, exitOK)
+		}
+
+		if got := stdout.String(); got != want.String() {
+			t.Errorf("run(%v) stdout = %q, want what scan %s prints, %q",
+				args, got, helpFlag, want.String())
+		}
+
+		if got := stderr.String(); got != "" {
+			t.Errorf("run(%v) stderr = %q, want nothing", args, got)
+		}
+	}
+}
+
 func TestRunScanUsageLine(t *testing.T) {
 	t.Parallel()
 
 	// README §Subcommands shows this usage line for scan, and the help
-	// and the usage error both print it.
+	// and the usage error both print it. TestRunHelp and
+	// TestRunUsageErrors check which stream each goes to.
 	const want = "\n  sfdupes scan [--workers N] [-x] [--no-default-excludes] " +
 		"[--exclude PATH]... PATH...\n"
 
@@ -764,13 +821,13 @@ func TestRunScanUsageLine(t *testing.T) {
 		t.Run(name, func(t *testing.T) {
 			t.Parallel()
 
-			var stdout, stderr bytes.Buffer
+			var output bytes.Buffer
 
-			run(args, &stdout, &stderr)
+			run(args, &output, &output)
 
-			if !strings.Contains(stderr.String(), want) {
+			if !strings.Contains(output.String(), want) {
-				t.Errorf("run(%v) stderr = %q, want the usage line %q",
+				t.Errorf("run(%v) output = %q, want the usage line %q",
-					args, stderr.String(), want)
+					args, output.String(), want)
 			}
 		})
 	}
@@ -836,9 +893,9 @@ func TestRunHelpDescribesOutput(t *testing.T) {
 		}
 
 		for _, want := range tc.want {
-			if !strings.Contains(stderr.String(), want) {
+			if !strings.Contains(stdout.String(), want) {
 				t.Errorf("run(%v) help lacks %q:\n%s",
-					args, want, stderr.String())
+					args, want, stdout.String())
 			}
 		}
 	}
@@ -922,6 +979,32 @@ func TestRunVersionWriteFailureIsFatal(t *testing.T) {
 	}
 }
 
+func TestRunHelpWriteFailureIsFatal(t *testing.T) {
+	t.Parallel()
+
+	// README §Error handling: a failed write to stdout is a fatal error,
+	// exit 1, reported on stderr starting with "sfdupes:". Help goes to
+	// stdout, so that holds for help too.
+	cases := [][]string{
+		{helpFlag}, {"-h"}, {helpCommand},
+		{cmdScan, helpFlag}, {helpCommand, cmdScan},
+	}
+
+	for _, args := range cases {
+		var stderr bytes.Buffer
+
+		code := run(args, failingWriter{}, &stderr)
+		if code != exitFatal {
+			t.Errorf("run(%v) = %d, want %d", args, code, exitFatal)
+		}
+
+		want := "sfdupes: write stdout: " + errWriteFailed.Error() + "\n"
+		if got := stderr.String(); got != want {
+			t.Errorf("run(%v) stderr = %q, want %q", args, got, want)
+		}
+	}
+}
+
 // scanFixture builds a small tree holding one duplicate pair and one
 // unreadable file and scans it into the database the caller has
 // pointed SFDUPES_DATABASE at. The unreadable file makes the scan warn
@@ -1013,8 +1096,7 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 
 	stderr := scanOK(t, dir)
 
-	warning := "hash " + unreadable + ": open " + unreadable +
+	warning := "scan: skipped " + unreadable + " (permission denied)\n"
-		": permission denied\n"
 	if !strings.Contains(stderr, warning) {
 		t.Errorf("stderr = %q, want %q", stderr, warning)
 	}
@@ -1286,7 +1368,7 @@ func TestRunScanSkipsSymlinkToFIFOOperand(t *testing.T) {
 
 	stderr := scanOK(t, link)
 
-	warning := "walk " + fifo + ": skipping FIFO operand\n"
+	warning := "scan: skipped " + fifo + " (a FIFO)\n"
 	if !strings.Contains(stderr, warning) {
 		t.Errorf("stderr = %q, want %q", stderr, warning)
 	}
@@ -1321,7 +1403,7 @@ func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
 
 	stderr := scanOK(t, operand)
 
-	warning := "walk " + operand + ": skipping " + kind + " operand\n"
+	warning := "scan: skipped " + operand + " (a " + kind + ")\n"
 	if !strings.Contains(stderr, warning) {
 		t.Errorf("stderr = %q, want %q", stderr, warning)
 	}
@@ -1355,7 +1437,7 @@ func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
 	writeFile(t, hourly, "f", pattern(1, 10))
 	f := writeFile(t, dir, "f", pattern(2, 10))
 
-	warning := "walk " + hourly + ": skipping operand inside a .zfs directory\n"
+	warning := "scan: skipped " + hourly + " (inside a .zfs directory)\n"
 
 	for _, tc := range []struct {
 		operands []string
@@ -1407,7 +1489,7 @@ func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
 	stderr := scanOK(t, filepath.Join(snaps, "daily"))
 
 	daily := filepath.Join(dir, "pool", ".zfs", "snapshot", "daily")
-	warning := "walk " + daily + ": skipping operand inside a .zfs directory\n"
+	warning := "scan: skipped " + daily + " (inside a .zfs directory)\n"
 	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
 		"0 unchanged), 1 skipped\n"
 

internal/sfdupes/dwim_test.go

@@ -121,9 +121,9 @@ func TestRunDwimExcludeLeavesTreeOut(t *testing.T) {
 		t.Errorf("group = %q, want it to start %q", lines[1], want)
 	}
 
-	skipped := "scan: skipped " + excluded + " (--exclude)\n"
+	leftOut := "scan: left out " + excluded + " (--exclude)\n"
-	if got := stderr(); !strings.Contains(got, skipped) {
+	if got := stderr(); !strings.Contains(got, leftOut) {
-		t.Errorf("stderr = %q, want it to contain %q", got, skipped)
+		t.Errorf("stderr = %q, want it to contain %q", got, leftOut)
 	}
 }
 
@@ -190,21 +190,21 @@ func TestRunDwimHelpListsScanFlags(t *testing.T) {
 
 	run([]string{cmdDwim, "-h"}, &stdout, &stderr)
 
-	if !strings.Contains(stderr.String(), want) {
+	if !strings.Contains(stdout.String(), want) {
-		t.Errorf("dwim -h stderr = %q, want the usage line %q",
+		t.Errorf("dwim -h stdout = %q, want the usage line %q",
-			stderr.String(), want)
+			stdout.String(), want)
 	}
 
-	if !strings.Contains(stderr.String(), excludeFlag+" PATH") {
+	if !strings.Contains(stdout.String(), excludeFlag+" PATH") {
-		t.Errorf("dwim -h stderr = %q, want %s PATH", stderr.String(),
+		t.Errorf("dwim -h stdout = %q, want %s PATH", stdout.String(),
 			excludeFlag)
 	}
 
 	// README "Settings": the help lists the default excludes and the
 	// filesystem types the walk never records anything on.
 	help := strings.TrimSpace(defaultExcludesHelp(runtime.GOOS))
-	if !strings.Contains(stderr.String(), help) {
+	if !strings.Contains(stdout.String(), help) {
-		t.Errorf("dwim -h stderr = %q, want it to hold %q", stderr.String(),
+		t.Errorf("dwim -h stdout = %q, want it to hold %q", stdout.String(),
 			help)
 	}
 }

internal/sfdupes/exclude.go

@@ -203,7 +203,7 @@ func (rules walkRules) excludePathLine(path string, fi fs.FileInfo) string {
 		return ""
 	}
 
-	return fmt.Sprintf("scan: skipped %s (--exclude)", path)
+	return fmt.Sprintf("scan: left out %s (--exclude)", path)
 }
 
 // nonPersistentFilesystemTypes returns the filesystem types that are
@@ -233,7 +233,7 @@ func (rules walkRules) nonPersistentLine(path string, fi fs.FileInfo) string {
 		return ""
 	}
 
-	return fmt.Sprintf("scan: skipped %s (%s, not a persistent filesystem)",
+	return fmt.Sprintf("scan: left out %s (%s, not a persistent filesystem)",
 		path, fsType)
 }
 

internal/sfdupes/exclude_test.go

@@ -196,8 +196,8 @@ func TestDefaultExcludesHelp(t *testing.T) {
 	run([]string{cmdScan, "-h"}, &stdout, &stderr)
 
 	help := strings.TrimSpace(defaultExcludesHelp(runtime.GOOS))
-	if !strings.Contains(stderr.String(), help) {
+	if !strings.Contains(stdout.String(), help) {
-		t.Errorf("scan --help = %q, want it to hold %q", stderr.String(), help)
+		t.Errorf("scan --help = %q, want it to hold %q", stdout.String(), help)
 	}
 }
 
@@ -242,7 +242,7 @@ func TestScanDoesNotEnterDefaultExclude(t *testing.T) {
 		t.Errorf("%s recorded: the walk entered %s", unseen, excluded)
 	}
 
-	line := "\nscan: skipped " + excluded + " (default exclude)\n"
+	line := "\nscan: left out " + excluded + " (default exclude)\n"
 	if !strings.Contains(stderr(), line) {
 		t.Errorf("stderr = %q, want %q", stderr(), line)
 	}
@@ -311,7 +311,7 @@ func TestScanNamesNoDefaultExcludeThatIsAnOperand(t *testing.T) {
 
 	recordByPath(t, dbRecords(t, db), f)
 
-	if strings.Contains(stderr(), "scan: skipped") {
+	if strings.Contains(stderr(), "scan: left out") {
 		t.Errorf("stderr = %q, want no line for %s", stderr(), excluded)
 	}
 }
@@ -332,8 +332,8 @@ func TestRunScanTempDirOperand(t *testing.T) {
 	f := writeFile(t, dir, "sub/f", pattern(1, 10))
 
 	stderr := scanOK(t, dir)
-	if strings.Contains(stderr, "scan: skipped") {
+	if strings.Contains(stderr, "scan: left out") {
-		t.Errorf("stderr = %q, want no line saying a path was skipped",
+		t.Errorf("stderr = %q, want no line saying a path was left out",
 			stderr)
 	}
 
@@ -377,7 +377,7 @@ func TestRunScanNoDefaultExcludes(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	line := "scan: skipped /var/tmp (default exclude)\n"
+	line := "scan: left out /var/tmp (default exclude)\n"
 
 	if stderr := scanOK(t, "/var"); !strings.Contains(stderr, line) {
 		t.Errorf("scan /var: stderr = %q, want %q", stderr, line)
@@ -418,7 +418,7 @@ func TestRunScanExcludeNested(t *testing.T) {
 
 	stderr := scanOK(t, excludeFlag, excluded, dir)
 
-	line := "scan: skipped " + excluded + " (--exclude)\n"
+	line := "scan: left out " + excluded + " (--exclude)\n"
 	if !strings.Contains(stderr, line) {
 		t.Errorf("stderr = %q, want %q", stderr, line)
 	}
@@ -480,8 +480,8 @@ func TestRunScanExcludeReachedByAnotherPath(t *testing.T) {
 	stderr := scanOK(t, excludeFlag, filepath.Join(link, "cache"),
 		excludeFlag, dotDot, dir)
 
-	for _, skipped := range []string{filepath.Dir(inDir), file, hardLink} {
+	for _, leftOut := range []string{filepath.Dir(inDir), file, hardLink} {
-		line := "scan: skipped " + skipped + " (--exclude)\n"
+		line := "scan: left out " + leftOut + " (--exclude)\n"
 		if !strings.Contains(stderr, line) {
 			t.Errorf("stderr = %q, want %q", stderr, line)
 		}
@@ -615,7 +615,7 @@ func TestRunScanSkipsNonPersistentOperand(t *testing.T) {
 
 	t.Setenv(databaseEnv, testDBPath(t))
 
-	line := "scan: skipped " + shm + " (" + fsType +
+	line := "scan: left out " + shm + " (" + fsType +
 		", not a persistent filesystem)\n"
 	summary := "scan: 0 files seen"
 
@@ -669,7 +669,7 @@ func TestScanKeepsRecordsOnNonPersistent(t *testing.T) {
 		t.Errorf("%s recorded", unseen)
 	}
 
-	line := "scan: skipped " + shm + " (" + fsType +
+	line := "scan: left out " + shm + " (" + fsType +
 		", not a persistent filesystem)\n"
 	if !strings.Contains(stderr(), line) {
 		t.Errorf("stderr = %q, want %q", stderr(), line)
@@ -702,7 +702,7 @@ func TestWalkLeavesOutNonPersistent(t *testing.T) {
 
 		leftOut = append(leftOut, ev.leftOut)
 
-		want := "scan: skipped " + ev.leftOut + " (" + fsType +
+		want := "scan: left out " + ev.leftOut + " (" + fsType +
 			", not a persistent filesystem)"
 		if ev.warn != want {
 			t.Errorf("line = %q, want %q", ev.warn, want)

internal/sfdupes/scan.go

@@ -664,8 +664,8 @@ func isDatabaseFile(f fileRec, rules walkRules) bool {
 // inode run, committing completed records to the database in batches
 // as results arrive, so a long scan persists its progress as it goes
 // (an interrupted scan resumes cheaply: the next run skips everything
-// already recorded). A run that fails to hash is warned about and
+// already recorded). Each path of a run that fails to hash is warned
-// counted as skipped; stale records for its paths, if any, are deleted
+// about and counted as skipped; stale records for them, if any, are deleted
 // by the update phase. A run whose file no longer exists gets no record
 // and no warning, and is not counted as skipped. The total counts actual
 // reads, so the display's time remaining is meaningful.
@@ -706,9 +706,12 @@ func (s *scanState) hashPhase(ctx context.Context, workers int) error {
 		}
 
 		if r.err != nil {
-			s.st.skipped += len(r.run)
+			// Every path in the run is counted, so every path gets a line.
+			for _, rec := range r.run {
+				s.st.skipped++
 
-			prog.warnf("hash %s: %v", r.run[0].path, r.err)
+				prog.warnf("%s", skippedLine(rec.path, r.err))
+			}
 
 			continue
 		}
@@ -915,8 +918,7 @@ func operandWarning(root string, fi fs.FileInfo) string {
 	// The walk never enters a .zfs directory, so it starts from nothing
 	// inside one either.
 	if slices.Contains(strings.Split(filepath.Dir(root), "/"), ".zfs") {
-		return fmt.Sprintf("walk %s: skipping operand inside a .zfs directory",
+		return fmt.Sprintf("scan: skipped %s (inside a .zfs directory)", root)
-			root)
 	}
 
 	var kind string
@@ -942,7 +944,21 @@ func operandWarning(root string, fi fs.FileInfo) string {
 		kind = "non-regular file"
 	}
 
-	return fmt.Sprintf("walk %s: skipping %s operand", root, kind)
+	return fmt.Sprintf("scan: skipped %s (a %s)", root, kind)
+}
+
+// skippedLine returns the warning for a path the scan skips because of
+// err. The reason is the error without its path, which the line already
+// names.
+func skippedLine(path string, err error) string {
+	reason := err.Error()
+
+	var pathErr *fs.PathError
+	if errors.As(err, &pathErr) {
+		reason = pathErr.Err.Error()
+	}
+
+	return fmt.Sprintf("scan: skipped %s (%s)", path, reason)
 }
 
 // seedRoot turns one PATH operand into the walk's starting state: a
@@ -965,7 +981,7 @@ func seedRoot(ctx context.Context, root string, rules walkRules,
 
 	if err != nil {
 		sendEvent(ctx, events, walkEvent{
-			warn: fmt.Sprintf("walk %s: %v", root, err),
+			warn: skippedLine(root, err),
 			fail: true,
 		})
 
@@ -1094,7 +1110,7 @@ func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
 
 	if err != nil {
 		sendEvent(ctx, events, walkEvent{
-			warn: fmt.Sprintf("walk %s: %v", job.path, err),
+			warn: skippedLine(job.path, err),
 			fail: true,
 		})
 
@@ -1153,7 +1169,7 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 
 	if err != nil {
 		sendEvent(ctx, events, walkEvent{
-			warn: fmt.Sprintf("stat %s: %v", p, err),
+			warn: skippedLine(p, err),
 			fail: true,
 		})
 
@@ -1214,7 +1230,7 @@ func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 
 	if err != nil {
 		sendEvent(ctx, events, walkEvent{
-			warn: fmt.Sprintf("walk %s: %v", p, err),
+			warn: skippedLine(p, err),
 			fail: true,
 		})
 
@@ -1235,7 +1251,7 @@ func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 	if isDefaultExclude(p, rules.defaultExcludes) {
 		sendEvent(ctx, events, walkEvent{
 			leftOut: p,
-			warn:    fmt.Sprintf("scan: skipped %s (default exclude)", p),
+			warn:    fmt.Sprintf("scan: left out %s (default exclude)", p),
 		})
 
 		return dirJob{}, false

internal/sfdupes/scan_test.go

@@ -752,8 +752,9 @@ func TestWalkPassesOverRemovedPaths(t *testing.T) {
 
 // TestScanWarnsAboutUnreadablePaths checks that a permission error is
 // still warned about and counted as skipped, unlike a removed path. The
-// walk reaches an unreadable directory, and a file in a directory that
+// walk reaches an unreadable directory. It also reaches a file and a
-// can be read but not searched. Another such file is an operand.
+// subdirectory in a directory that can be read but not searched. Another
+// such file is an operand.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestScanWarnsAboutUnreadablePaths(t *testing.T) {
@@ -765,6 +766,7 @@ func TestScanWarnsAboutUnreadablePaths(t *testing.T) {
 	dir := t.TempDir()
 	tree := filepath.Join(dir, "tree")
 	walked := writeFile(t, tree, "unsearchable/f", []byte("x"))
+	subdir := filepath.Join(filepath.Dir(walked), "d")
 	operand := writeFile(t, dir, "unsearchable/f", []byte("y"))
 	unreadable := filepath.Join(tree, "unreadable")
 
@@ -773,6 +775,11 @@ func TestScanWarnsAboutUnreadablePaths(t *testing.T) {
 		t.Fatal(err)
 	}
 
+	err = os.Mkdir(subdir, 0o750)
+	if err != nil {
+		t.Fatal(err)
+	}
+
 	modes := map[string]fs.FileMode{
 		unreadable:            0,
 		filepath.Dir(walked):  0o400,
@@ -793,15 +800,16 @@ func TestScanWarnsAboutUnreadablePaths(t *testing.T) {
 	}
 
 	st := syncTree(t, openTestDB(t), tree, operand)
-	if st != (scanStats{skipped: 3}) {
+	if st != (scanStats{skipped: 4}) {
-		t.Errorf("stats = %+v, want 3 skipped and nothing else", st)
+		t.Errorf("stats = %+v, want 4 skipped and nothing else", st)
 	}
 
 	got := stderr()
 	for _, warning := range []string{
-		"walk " + unreadable + ": open " + unreadable + ": permission denied\n",
+		"scan: skipped " + unreadable + " (permission denied)\n",
-		"stat " + walked + ": lstat " + walked + ": permission denied\n",
+		"scan: skipped " + walked + " (permission denied)\n",
-		"walk " + operand + ": lstat " + operand + ": permission denied\n",
+		"scan: skipped " + subdir + " (permission denied)\n",
+		"scan: skipped " + operand + " (permission denied)\n",
 	} {
 		if !strings.Contains(got, warning) {
 			t.Errorf("stderr = %q, want %q", got, warning)
@@ -1941,14 +1949,19 @@ func TestScanHardlinksReadOnce(t *testing.T) {
 	}
 }
 
+// TestScanHardlinkRunFailsTogether makes a file with two hard links
+// unreadable. Both paths are counted as skipped, and each gets its own
+// warning.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestScanHardlinkRunFailsTogether(t *testing.T) {
-	t.Parallel()
+	stderr := captureStderr(t)
-
 	dir := t.TempDir()
 	db := openTestDB(t)
 	a := writeFile(t, dir, "a.bin", pattern(1, 300))
+	b := filepath.Join(dir, "b.bin")
 
-	err := os.Link(a, filepath.Join(dir, "b.bin"))
+	err := os.Link(a, b)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -1964,6 +1977,15 @@ func TestScanHardlinkRunFailsTogether(t *testing.T) {
 	if st.skipped != 2 || st.added != 0 {
 		t.Fatalf("stats = %+v, want both hardlink paths skipped", st)
 	}
+
+	got := stderr()
+
+	for _, p := range []string{a, b} {
+		warning := "scan: skipped " + p + " (permission denied)\n"
+		if !strings.Contains(got, warning) {
+			t.Errorf("stderr = %q, want %q", got, warning)
+		}
+	}
 }
 
 // TestHashPhaseSkipsFileReplacedByFIFO replaces a walked regular file
@@ -2001,7 +2023,7 @@ func TestHashPhaseSkipsFileReplacedByFIFO(t *testing.T) {
 			s.st.skipped, len(s.batch))
 	}
 
-	warning := "hash " + p + ": not a regular file\n"
+	warning := "scan: skipped " + p + " (not a regular file)\n"
 	if got := stderr(); strings.Count(got, warning) != 1 {
 		t.Errorf("stderr = %q, want %q once", got, warning)
 	}