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

@@ -146,33 +146,44 @@ 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, with the working directory, its symlinks resolved, put in front
-// of it when it is relative, and where the path came from, "default" or
-// "from SFDUPES_DATABASE", for the line each subcommand prints first on
-// stderr.
+// path, made absolute by absolutePath, and where the path came from,
+// "default" or "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
 	}
 
-	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()
+	abs, err := absolutePath(path)
 	if err != nil {
 		return "", "", fmt.Errorf("resolve database path %s: %w", path, err)
 	}
 
-	// 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.
+	return abs, source, nil
+}
+
+// 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, source, nil
+	return strings.TrimSuffix(wd, "/") + "/" + path, nil
 }
 
 // createDatabaseDirectory creates the directory the database at path

scan.go

@@ -18,8 +18,6 @@ import (
 	"sync"
 	"syscall"
 	"time"
-
-	"golang.org/x/sys/unix"
 )
 
 // The hash phase gives every file it reads three hashes (see
@@ -221,22 +219,9 @@ func resolveRoots(roots []string) ([]string, error) {
 	resolved := make([]string, 0, len(roots))
 
 	for _, root := range roots {
-		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
+		a, err := absolutePath(root)
+		if err != nil {
+			return nil, fmt.Errorf("resolve %s: %w", root, err)
 		}
 
 		r, err := filepath.EvalSymlinks(a)

scan_test.go

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