Say "skipped" in scan's warnings for skipped paths (closes #170)

A warning for a path the summary counts as skipped now reads
`scan: skipped PATH (REASON)`, naming the path once. This covers
unreadable directories, failed lstats, failed reads and dropped
operands. Each path of a hard-linked file that cannot be read gets its
own line, since each is counted. Lines for paths left out on purpose
(`--exclude`, default excludes, filesystems that are not persistent)
now read `scan: left out PATH (...)`, so a search for `scan: skipped`
finds only the counted paths.

Model: opus-5-5

README.md

@@ -563,7 +563,7 @@ 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 +573,7 @@ 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 +622,7 @@ 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 +682,18 @@ 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_test.go

@@ -1013,8 +1013,7 @@ 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 +1285,7 @@ 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 +1320,7 @@ 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 +1354,7 @@ 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 +1406,7 @@ 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)
 	}
 }
 

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

@@ -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)
 	}