Add scan --exclude PATH (closes #163) (#165)

internal/sfdupes/scan.go

@@ -102,40 +102,44 @@ func scanPhase(name string) string {
 // scan command rejects anything less. Before the lock is taken, the
 // scan lists the filesystems that are not persistent, on which the walk
 // records nothing; unless noDefaultExcludes is set, the walk does not
-// enter the default excludes either. Once the database is open, the
-// scan notes its files, which the walk passes over.
+// enter the default excludes either. The walk neither enters nor
+// records the paths in excludePaths, the --exclude values; an operand
+// at or below one is a fatal error. Once the database is open, the scan
+// notes its files, which the walk passes over.
 func runScan(ctx context.Context, roots []string, workers int,
-	oneFS, noDefaultExcludes bool,
+	oneFS, noDefaultExcludes bool, excludePaths []string,
 ) error {
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
 	}
 
-	// A database file missing now is created by lockScanDatabase below.
-	what := "database"
+	printDatabasePath(dbPath, source)
 
-	_, err = os.Stat(dbPath)
-	if errors.Is(err, fs.ErrNotExist) {
-		what = "new database"
-	}
-
-	fmt.Fprintf(os.Stderr, "scan: %s %s (%s)\n", what, escapePath(dbPath),
-		source)
-
-	roots, err = resolveRoots(roots)
+	roots, err = realPaths(roots)
 	if err != nil {
 		return err
 	}
 
-	nonPersistent, err := nonPersistentFilesystems()
+	var rules walkRules
+
+	rules.excludePaths, err = excludePathInodes(excludePaths)
+	if err != nil {
+		return fmt.Errorf("--exclude: %w", err)
+	}
+
+	err = checkOperandsNotExcluded(roots, rules.excludePaths)
+	if err != nil {
+		return err
+	}
+
+	rules.nonPersistent, err = nonPersistentFilesystems()
 	if err != nil {
 		return fmt.Errorf("list the mounted filesystems: %w", err)
 	}
 
-	rules := walkRules{nonPersistent: nonPersistent}
 	if !noDefaultExcludes {
-		rules.excludes = defaultExcludes(runtime.GOOS)
+		rules.defaultExcludes = defaultExcludes(runtime.GOOS)
 	}
 
 	lock, err := lockScanDatabase(dbPath)
@@ -181,6 +185,21 @@ func runScan(ctx context.Context, roots []string, workers int,
 	return nil
 }
 
+// printDatabasePath prints on stderr the line that names the database
+// at dbPath, with source, saying whether it is new. A database file
+// missing now is new: lockScanDatabase creates it.
+func printDatabasePath(dbPath, source string) {
+	what := "database"
+
+	_, err := os.Stat(dbPath)
+	if errors.Is(err, fs.ErrNotExist) {
+		what = "new database"
+	}
+
+	fmt.Fprintf(os.Stderr, "scan: %s %s (%s)\n", what, escapePath(dbPath),
+		source)
+}
+
 // interruptContext returns a copy of ctx that the first SIGINT or
 // SIGTERM cancels; the scan command runs the scan under it. stop
 // releases the signals.
@@ -209,24 +228,25 @@ func interrupted(walked int) error {
 	return errInterrupted
 }
 
-// resolveRoots converts each PATH operand to its real path: absolute,
-// with every symlink in it followed. Database records are keyed by
-// that path, so scan results depend neither on the working directory
-// nor on the symlinks an operand was given through. An operand that
-// cannot be resolved, because it or a symlink's target does not exist
-// or cannot be read, is a fatal error before any scanning.
-func resolveRoots(roots []string) ([]string, error) {
-	resolved := make([]string, 0, len(roots))
+// realPaths returns the real path of each of paths, the PATH operands
+// or the --exclude values: absolute, with every symlink in it followed.
+// Database records are keyed by that path, so scan results depend
+// neither on the working directory nor on the symlinks an operand was
+// given through. A path that cannot be resolved, because it or a
+// symlink's target does not exist or cannot be read, is a fatal error
+// before any scanning.
+func realPaths(paths []string) ([]string, error) {
+	resolved := make([]string, 0, len(paths))
 
-	for _, root := range roots {
-		a, err := absolutePath(root)
+	for _, path := range paths {
+		a, err := absolutePath(path)
 		if err != nil {
-			return nil, fmt.Errorf("resolve %s: %w", root, err)
+			return nil, fmt.Errorf("resolve %s: %w", path, err)
 		}
 
 		r, err := filepath.EvalSymlinks(a)
 		if err != nil {
-			return nil, fmt.Errorf("resolve %s: %w", root, err)
+			return nil, fmt.Errorf("resolve %s: %w", path, err)
 		}
 
 		resolved = append(resolved, r)
@@ -295,7 +315,7 @@ func walkReaches(above, r string, oneFS bool, rules walkRules,
 	}
 
 	for ; dir != above; dir = filepath.Dir(dir) {
-		if isDefaultExclude(dir, rules.excludes) {
+		if isDefaultExclude(dir, rules.defaultExcludes) {
 			return false
 		}
 
@@ -418,7 +438,7 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
 
 // walkableRoots returns the operands the walk can start from: regular
 // files, and directories not named .zfs, none of them inside a
-// directory named .zfs. The operands are real paths from resolveRoots,
+// directory named .zfs. The operands are real paths from realPaths,
 // so these checks apply to what a symlink operand points at. 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
@@ -493,10 +513,11 @@ func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
 // as verified. When its disk_size differs from the record's, it is
 // queued for the update phase, which writes the new disk_size. A record
 // at or below a path the walk left out, because -x stopped at it, it is
-// a default exclude, or it is not on a persistent filesystem, counts as
-// outside the roots: it is not deleted. That does not hold below a root
-// at or inside that path, since that root's own walk verifies the
-// records below it; nor is a line printed for such a root.
+// an --exclude path or a default exclude, or it is not on a persistent
+// filesystem, counts as outside the roots: it is not deleted. That does
+// not hold below a root at or inside that path, since that root's own
+// walk verifies the records below it; nor is a line printed for such a
+// root.
 func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 	// The records the last scan left under the roots estimate how many
 	// files the walk will find. A first scan has none, and no estimate.
@@ -834,9 +855,9 @@ type dirJob struct {
 // file's statted record, a warning when fail is set, or a path the walk
 // left out: when otherFSDir is set, a directory -x did not enter
 // because it is on another filesystem than its operand, and when
-// leftOut is set, a default exclude or a directory or file on a
-// filesystem that is not persistent, with warn holding the line that
-// says so.
+// leftOut is set, an --exclude path, a default exclude or a directory or
+// file on a filesystem that is not persistent, with warn holding the
+// line that says so.
 type walkEvent struct {
 	rec        fileRec
 	warn       string
@@ -887,7 +908,7 @@ 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, that is not
-// inside a directory named .zfs. resolveRoots has already followed the
+// inside a directory named .zfs. realPaths has already followed the
 // operand's symlinks, so a symlink here is an operand replaced by one
 // after it was resolved, and is not followed.
 func operandWarning(root string, fi fs.FileInfo) string {
@@ -1118,8 +1139,9 @@ func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
 // no longer exists, and one that has stopped being a regular file is
 // skipped. A file on a filesystem in rules that is not persistent, as
 // through a bind mount of one file, is not recorded: it gets an event
-// naming it instead. One of the scan's own database files in rules gets
-// no event at all.
+// naming it instead, and so does a file given with --exclude, reached
+// by any path, a hard link to it included. One of the scan's own
+// database files in rules gets no event at all.
 func emitFile(ctx context.Context, p string, e fs.DirEntry,
 	rules walkRules, events chan<- walkEvent,
 ) {
@@ -1143,6 +1165,10 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 	}
 
 	line := rules.nonPersistentLine(p, info)
+	if line == "" {
+		line = rules.excludePathLine(p, info)
+	}
+
 	if line != "" {
 		sendEvent(ctx, events, walkEvent{leftOut: p, warn: line})
 
@@ -1167,11 +1193,11 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 // subdirJob applies the descent rules to directory p: never enter
 // .zfs (ZFS snapshot pseudo-dirs would list every file once per
 // snapshot), never enter a directory on a filesystem in rules that is
-// not persistent, nor a default exclude in rules, and with -x never
-// enter a directory on a different filesystem than its operand. For the
-// last three it sends an event that names the directory, so the scan
-// keeps the records below it, except those below an operand at or
-// inside it.
+// not persistent, nor an --exclude path or a default exclude in rules,
+// and with -x never enter a directory on a different filesystem than
+// its operand. For all but .zfs it sends an event that names the
+// directory, so the scan keeps the records below it, except those below
+// an operand at or inside it.
 func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 	parent dirJob, oneFS bool, rules walkRules,
 	events chan<- walkEvent,
@@ -1196,13 +1222,17 @@ func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 	}
 
 	line := rules.nonPersistentLine(p, info)
+	if line == "" {
+		line = rules.excludePathLine(p, info)
+	}
+
 	if line != "" {
 		sendEvent(ctx, events, walkEvent{leftOut: p, warn: line})
 
 		return dirJob{}, false
 	}
 
-	if isDefaultExclude(p, rules.excludes) {
+	if isDefaultExclude(p, rules.defaultExcludes) {
 		sendEvent(ctx, events, walkEvent{
 			leftOut: p,
 			warn:    fmt.Sprintf("scan: skipped %s (default exclude)", p),