Resolve scan operands to their real paths (closes #144)

scan now resolves every operand with its symlinks followed before the
walk, and uses that real path for pruning, walking, records and
warnings. A relative operand is joined to the working directory as the
kernel reports it, so a ".." after a symlink counts from its target, as
with realpath. A symlink operand is scanned at its target instead of
skipped. An operand given through a symlink below another operand, to a
directory outside it, is walked on its own instead of dropped with its
records deleted. An operand that cannot be resolved is a fatal error
naming the operand as given. The walk itself still follows no symlink.

Model: opus-5-5

db.go

@@ -146,44 +146,33 @@ var errHashSize = errors.New("hash is not 32 bytes")
 
 // databasePath resolves the database location: SFDUPES_DATABASE when
 // set and non-empty, the compiled-in default otherwise. It returns the
-// path, made absolute by absolutePath, and where the path came from,
+// path, with the working directory, its symlinks resolved, put in front
-// "default" or "from SFDUPES_DATABASE", for the line each subcommand
+// of it when it is relative, and where the path came from, "default" or
-// prints first on stderr.
+// "from SFDUPES_DATABASE", for the line each subcommand prints first on
+// stderr.
 func databasePath() (string, string, error) {
 	path, source := defaultDatabasePath, "default"
 	if p := os.Getenv(databaseEnv); p != "" {
 		path, source = p, "from "+databaseEnv
 	}
 
-	abs, err := absolutePath(path)
+	if filepath.IsAbs(path) {
+		return path, source, nil
+	}
+
+	// The working directory as the kernel reports it, with no symlink
+	// in it, as README "Database" says. os.Getwd may return PWD
+	// instead, which can name it through a symlink.
+	wd, err := unix.Getwd()
 	if err != nil {
 		return "", "", fmt.Errorf("resolve database path %s: %w", path, err)
 	}
 
-	return abs, source, nil
+	// Not filepath.Abs or filepath.Join: they clean the path, which
-}
+	// drops each ".." together with the directory name before it. When
-
+	// that directory is a symlink, the cleaned path names another file.
-// absolutePath returns path unchanged when it is absolute, and
-// otherwise the working directory, a "/" and path. The working
-// directory is the one the kernel reports, with no symlink in it;
-// os.Getwd may return PWD instead, which can name it through a symlink.
-// The result is not cleaned, as filepath.Abs and filepath.Join would
-// clean it. Cleaning drops each ".." together with the directory name
-// before it. When that name is a symlink, the cleaned path names
-// another file than the one the system reaches by following the symlink
-// first.
-func absolutePath(path string) (string, error) {
-	if filepath.IsAbs(path) {
-		return path, nil
-	}
-
-	wd, err := unix.Getwd()
-	if err != nil {
-		return "", err
-	}
-
 	// The working directory ends in "/" only when it is the root.
-	return strings.TrimSuffix(wd, "/") + "/" + path, nil
+	return strings.TrimSuffix(wd, "/") + "/" + path, source, nil
 }
 
 // createDatabaseDirectory creates the directory the database at path

scan.go

@@ -18,6 +18,8 @@ import (
 	"sync"
 	"syscall"
 	"time"
+
+	"golang.org/x/sys/unix"
 )
 
 // The hash phase gives every file it reads three hashes (see
@@ -219,11 +221,24 @@ func resolveRoots(roots []string) ([]string, error) {
 	resolved := make([]string, 0, len(roots))
 
 	for _, root := range roots {
-		a, err := absolutePath(root)
+		a := root
+		if !filepath.IsAbs(a) {
+			// The working directory as the kernel reports it, with no
+			// symlink in it. os.Getwd may return PWD instead, which can
+			// name it through a symlink.
+			wd, err := unix.Getwd()
 			if err != nil {
 				return nil, fmt.Errorf("resolve %s: %w", root, err)
 			}
 
+			// Not filepath.Abs or filepath.Join: they clean the path,
+			// which drops each ".." together with the directory name
+			// before it. EvalSymlinks follows a symlink before it
+			// applies the ".." after it, as realpath does. The working
+			// directory ends in "/" only when it is the root.
+			a = strings.TrimSuffix(wd, "/") + "/" + root
+		}
+
 		r, err := filepath.EvalSymlinks(a)
 		if err != nil {
 			return nil, fmt.Errorf("resolve %s: %w", root, err)

scan_test.go

@@ -2310,24 +2310,34 @@ func TestUnderRoot(t *testing.T) {
 }
 
 // TestRunScanPassesOverDatabase scans a tree that holds the scan's own
-// database, and in one case also a hard link to the database file. The
+// database, given directly and through a symlinked directory, which
-// walk knows the database's files by device ID and inode number, so it
+// the scan resolves to the same real path. The walk passes over the
-// passes over the database file, its -wal and -shm files, its .lock
+// database file, its -wal and -shm files and its .lock file with no
-// file and the hard link with no line and no count. The record an
+// line and no count, and the record an earlier scan left for the .lock
-// earlier scan left for the .lock file is deleted. A rescan of the
+// file is deleted. A rescan of the unchanged tree updates nothing, and
-// unchanged tree updates nothing, and report lists none of the
+// report lists none of the database's files.
-// database's files.
 func TestRunScanPassesOverDatabase(t *testing.T) {
-	for _, viaHardLink := range []bool{false, true} {
+	for _, viaSymlink := range []bool{false, true} {
-		t.Run(fmt.Sprintf("via hard link %v", viaHardLink), func(t *testing.T) {
+		t.Run(fmt.Sprintf("via symlink %v", viaSymlink), func(t *testing.T) {
-			tree := realTempDir(t)
+			base := realTempDir(t)
-			hardLink := filepath.Join(tree, "hardlink")
+			tree := filepath.Join(base, "real", "tree")
+			operand := tree
 
 			writeFile(t, tree, "a", pattern(1, 100))
 			writeFile(t, tree, "b", pattern(1, 100))
 			writeFile(t, tree, "empty1", nil)
 			writeFile(t, tree, "empty2", nil)
 
+			if viaSymlink {
+				err := os.Symlink(filepath.Join(base, "real"),
+					filepath.Join(base, "link"))
+				if err != nil {
+					t.Fatal(err)
+				}
+
+				operand = filepath.Join(base, "link", "tree")
+			}
+
 			dbPath := filepath.Join(tree, "db.sqlite")
 			t.Setenv(databaseEnv, dbPath)
 
@@ -2345,28 +2355,15 @@ func TestRunScanPassesOverDatabase(t *testing.T) {
 
 			closeScanDatabase(t.Context(), db, dbPath)
 
-			if viaHardLink {
+			assertScanSummary(t,
-				err = os.Link(dbPath, hardLink)
-				if err != nil {
-					t.Fatal(err)
-				}
-			}
-
-			stderr := assertScanSummary(t,
 				"4 files seen (4 added, 0 updated, 1 removed, 0 unchanged)",
-				tree)
+				operand)
-			stderr += assertScanSummary(t,
+			assertScanSummary(t,
 				"4 files seen (0 added, 0 updated, 0 removed, 4 unchanged)",
-				tree)
+				operand)
-
-			if strings.Contains(stderr, hardLink) {
-				t.Errorf("scan stderr = %q, want no line naming %s",
-					stderr, hardLink)
-			}
 
 			report := runStdout(t, cmdReport)
 			if strings.Contains(report, "db.sqlite") ||
-				strings.Contains(report, hardLink) ||
 				!strings.Contains(report, filepath.Join(tree, "empty2")) {
 				t.Errorf("report = %q, want the empty files and none of "+
 					"the database's files", report)
@@ -2392,9 +2389,8 @@ func TestRunScanPassesOverDatabaseOperands(t *testing.T) {
 
 // assertScanSummary scans operands and fails the test unless the
 // summary line gives counts with nothing skipped, and the line naming
-// the database is the only one that names one of its files. It returns
+// the database is the only one that names one of its files.
-// everything the scan printed to stderr.
+func assertScanSummary(t *testing.T, counts string, operands ...string) {
-func assertScanSummary(t *testing.T, counts string, operands ...string) string {
 	t.Helper()
 
 	stderr := scanOK(t, operands...)
@@ -2408,6 +2404,4 @@ func assertScanSummary(t *testing.T, counts string, operands ...string) string {
 		t.Errorf("scan %q: stderr = %q, want only the line naming the "+
 			"database to name one of its files", operands, stderr)
 	}
-
-	return stderr
 }