Warn about and skip non-regular and .zfs operands, keeping their records (closes #9)

A symlink, socket, FIFO or device-node operand, or a directory operand
named .zfs, was ignored without a word and stayed in the scanned
operands, so the update phase deleted every record stored beneath it.
Such an operand now gets a one-line warning naming the path and what it
is, counts as skipped in the summary, and is dropped before the
database index is loaded, so the records beneath it are left alone
unless it lies under another operand. The exit status stays 0. An
operand that turns into one of these between that check and the walk
is warned about and skipped by the walk instead. README "scan mode"
and "Rules for the walk" say so.

Model: opus-5-5

scan.go

@@ -210,14 +210,16 @@ type scanState struct {
 // in the content hash of every record of headTailMin or more whose
 // size, head, and tail match another record's). Records outside the
 // roots are never touched, except that the content phase fills in
-// their content hash.
+// their content hash. Operands the walk cannot start from are dropped
+// first, so the records beneath them count as outside the roots unless
+// they lie under another root.
 func syncScan(ctx context.Context, db *sql.DB, roots []string,
 	workers int, oneFS bool,
 ) (scanStats, error) {
-	roots = pruneRoots(roots)
-
 	s := &scanState{db: db}
 
+	roots = pruneRoots(s.walkableRoots(roots))
+
 	err := s.loadIndex(ctx, roots)
 	if err != nil {
 		return s.st, err
@@ -253,6 +255,35 @@ func syncScan(ctx context.Context, db *sql.DB, roots []string,
 	return s.st, s.contentPhase(ctx, workers)
 }
 
+// walkableRoots returns the operands the walk can start from: regular
+// files, and directories not named .zfs. Every other operand is warned
+// about, counted as skipped, and dropped. A dropped operand is no
+// longer a root, so the records stored beneath it are left as they are
+// instead of being deleted as unverified, unless it lies under another
+// root. An operand that fails lstat here is kept, and the walk warns
+// about it.
+func (s *scanState) walkableRoots(roots []string) []string {
+	kept := make([]string, 0, len(roots))
+
+	for _, root := range roots {
+		fi, err := os.Lstat(root)
+		if err == nil {
+			warn := operandWarning(root, fi)
+			if warn != "" {
+				s.st.skipped++
+
+				fmt.Fprintln(os.Stderr, escapePath(warn))
+
+				continue
+			}
+		}
+
+		kept = append(kept, root)
+	}
+
+	return kept
+}
+
 // loadIndex indexes the database records under the scan roots for
 // change detection and collects the sizes of every record outside
 // them: out-of-scope records join the size census so a scanned file
@@ -789,11 +820,43 @@ func sendEvent(ctx context.Context, events chan<- walkEvent,
 	}
 }
 
+// operandWarning returns the one-line warning for an operand the walk
+// does not start from, naming the path and what it is, or "" for one it
+// does: a regular file, or a directory not named .zfs. Symlinks are
+// never followed, including as operands.
+func operandWarning(root string, fi fs.FileInfo) string {
+	var kind string
+
+	switch mode := fi.Mode(); {
+	case mode.IsRegular():
+		return ""
+	case mode.IsDir():
+		if filepath.Base(root) != ".zfs" {
+			return ""
+		}
+
+		kind = ".zfs directory"
+	case mode&fs.ModeSymlink != 0:
+		kind = "symlink"
+	case mode&fs.ModeSocket != 0:
+		kind = "socket"
+	case mode&fs.ModeNamedPipe != 0:
+		kind = "FIFO"
+	case mode&fs.ModeDevice != 0:
+		kind = "device node"
+	default:
+		kind = "non-regular file"
+	}
+
+	return fmt.Sprintf("walk %s: skipping %s operand", root, kind)
+}
+
 // seedRoot turns one PATH operand into the walk's starting state: a
-// regular-file operand is statted and emitted directly, a directory
-// operand becomes an initial job, and a symlink or other non-regular
-// operand yields nothing (symlinks are never followed, including as
-// operands).
+// regular-file operand is statted and emitted directly, and a directory
+// operand becomes an initial job. walkableRoots has already dropped
+// every other operand. One that has changed into something else since
+// is warned about and skipped here; it is still a root, so the records
+// stored beneath it are deleted as unverified.
 func seedRoot(ctx context.Context, root string,
 	events chan<- walkEvent,
 ) []dirJob {
@@ -807,30 +870,30 @@ func seedRoot(ctx context.Context, root string,
 		return nil
 	}
 
-	switch {
-	case fi.IsDir():
-		if filepath.Base(root) == ".zfs" {
-			return nil
-		}
+	warn := operandWarning(root, fi)
+	if warn != "" {
+		sendEvent(ctx, events, walkEvent{warn: warn, fail: true})
 
+		return nil
+	}
+
+	if fi.IsDir() {
 		dev, ok := deviceOfInfo(fi)
 
 		return []dirJob{{path: root, rootDev: dev, rootDevOK: ok}}
-	case fi.Mode().IsRegular():
-		dev, ino := inodeOfInfo(fi)
-
-		sendEvent(ctx, events, walkEvent{rec: fileRec{
-			path:  root,
-			size:  fi.Size(),
-			mtime: fi.ModTime().Unix(),
-			dev:   dev,
-			ino:   ino,
-		}})
-
-		return nil
-	default:
-		return nil
 	}
+
+	dev, ino := inodeOfInfo(fi)
+
+	sendEvent(ctx, events, walkEvent{rec: fileRec{
+		path:  root,
+		size:  fi.Size(),
+		mtime: fi.ModTime().Unix(),
+		dev:   dev,
+		ino:   ino,
+	}})
+
+	return nil
 }
 
 // startWalkWorkers starts the walk worker pool. Each worker processes