fastwalk: add optional sorting and improve documentation

adapters.go

@@ -18,18 +18,17 @@ func isDir(path string, d fs.DirEntry) bool {
 	return false
 }
 
-// IgnoreDuplicateDirs wraps fs.WalkDirFunc walkFn to make it follow symbolic
+// IgnoreDuplicateDirs wraps [fs.WalkDirFunc] walkFn to make it follow symbolic
 // links and ignore duplicate directories (if a symlink points to a directory
 // that has already been traversed it is skipped). The walkFn is called for
 // for skipped directories, but the directory is not traversed (this is
 // required for error handling).
 //
-// The Config.Follow setting has no effect on the behavior of Walk when
+// The Follow [Config] setting has no effect on the behavior of Walk when
 // this wrapper is used.
 //
-// In most use cases, the returned fs.WalkDirFunc should not be reused between
-// in another call to Walk. If it is reused, any previously visited file will
-// be skipped.
+// In most use cases, the returned [fs.WalkDirFunc] should not be reused.
+// If it is reused, any previously visited file will be skipped.
 //
 // NOTE: The order of traversal is undefined. Given an "example" directory
 // like the one below where "dir" is a directory and "smydir1" and "smydir2"
@@ -68,9 +67,8 @@ func IgnoreDuplicateDirs(walkFn fs.WalkDirFunc) fs.WalkDirFunc {
 // files are ignored. If a symlink resolves to a file that has already been
 // visited it will be skipped.
 //
-// In most use cases, the returned fs.WalkDirFunc should not be reused between
-// in another call to Walk. If it is reused, any previously visited file will
-// be skipped.
+// In most use cases, the returned [fs.WalkDirFunc] should not be reused.
+// If it is reused, any previously visited file will be skipped.
 //
 // This can significantly slow Walk as os.Stat() is called for each path
 // (on Windows, os.Stat() is only needed for symlinks).
@@ -92,8 +90,8 @@ func IgnoreDuplicateFiles(walkFn fs.WalkDirFunc) fs.WalkDirFunc {
 	}
 }
 
-// IgnorePermissionErrors wraps walkFn so that permission errors are ignored.
-// The returned fs.WalkDirFunc may be reused.
+// IgnorePermissionErrors wraps walkFn so that [fs.ErrPermission] permission
+// errors are ignored. The returned [fs.WalkDirFunc] may be reused.
 func IgnorePermissionErrors(walkFn fs.WalkDirFunc) fs.WalkDirFunc {
 	return func(path string, d fs.DirEntry, err error) error {
 		if err != nil && os.IsPermission(err) {

dirent.go

@@ -31,11 +31,16 @@ func loadFileInfo(pinfo **fileInfo) *fileInfo {
 	return fi
 }
 
-// StatDirEntry returns the fs.FileInfo for the file or subdirectory described
-// by the entry.  If the entry is a symbolic link, StatDirEntry returns the
-// fs.FileInfo for the file the line references (os.Stat).
-// If fs.DirEntry de is a fastwalk.DirEntry it's Stat() method is used and the
-// returned fs.FileInfo may be a previously cached result.
+// StatDirEntry returns a [fs.FileInfo] describing the named file ([os.Stat]).
+// If de is a [fastwalk.DirEntry] its Stat method is used and the returned
+// FileInfo may be cached from a prior call to Stat. If a cached result is not
+// desired, users should just call [os.Stat] directly.
+//
+// This is a helper function for calling Stat on the DirEntry passed to the
+// walkFn argument to [Walk].
+//
+// The path argument is only used if de is not of type [fastwalk.DirEntry].
+// Therefore, de should be the DirEntry describing path.
 func StatDirEntry(path string, de fs.DirEntry) (fs.FileInfo, error) {
 	if de == nil {
 		return nil, &os.PathError{Op: "stat", Path: path, Err: syscall.EINVAL}

dirent_portable.go

@@ -1,37 +1,123 @@
 //go:build !darwin && !(aix || dragonfly || freebsd || (js && wasm) || linux || netbsd || openbsd || solaris)
 
+// TODO: add a "portable_dirent" build tag so that we can test this
+// on non-Windows platforms
+
 package fastwalk
 
 import (
 	"io/fs"
 	"os"
+	"slices"
+	"strings"
+	"sync"
 )
 
+var _ DirEntry = (*portableDirent)(nil)
+
 type portableDirent struct {
 	fs.DirEntry
-	path string
-	stat *fileInfo
+	parent string
+	stat   *fileInfo
+}
+
+func (d *portableDirent) String() string {
+	return fs.FormatDirEntry(d)
 }
 
-// TODO: cache the result of Stat
 func (d *portableDirent) Stat() (fs.FileInfo, error) {
 	if d.DirEntry.Type()&os.ModeSymlink == 0 {
 		return d.DirEntry.Info()
 	}
 	stat := loadFileInfo(&d.stat)
 	stat.once.Do(func() {
-		stat.FileInfo, stat.err = os.Stat(d.path)
+		stat.FileInfo, stat.err = os.Stat(d.parent + string(os.PathSeparator) + d.Name())
 	})
 	return stat.FileInfo, stat.err
 }
 
-func newDirEntry(dirName string, info fs.DirEntry) fs.DirEntry {
+func newDirEntry(dirName string, info fs.DirEntry) DirEntry {
 	return &portableDirent{
 		DirEntry: info,
-		path:     dirName + string(os.PathSeparator) + info.Name(),
+		parent:   dirName,
 	}
 }
 
-func fileInfoToDirEntry(dirname string, fi fs.FileInfo) fs.DirEntry {
+func fileInfoToDirEntry(dirname string, fi fs.FileInfo) DirEntry {
 	return newDirEntry(dirname, fs.FileInfoToDirEntry(fi))
 }
+
+var direntSlicePool = sync.Pool{
+	New: func() any {
+		a := make([]DirEntry, 0, 32)
+		return &a
+	},
+}
+
+func putDirentSlice(p *[]DirEntry) {
+	// max is half as many as Unix because twice the size
+	if p != nil && cap(*p) <= 16*1024 {
+		a := *p
+		for i := range a {
+			a[i] = nil
+		}
+		*p = a[:0]
+		direntSlicePool.Put(p)
+	}
+}
+
+func sortDirents(mode SortMode, dents []DirEntry) {
+	if len(dents) <= 1 {
+		return
+	}
+	switch mode {
+	case SortLexical:
+		slices.SortFunc(dents, func(d1, d2 DirEntry) int {
+			return strings.Compare(d1.Name(), d2.Name())
+		})
+	case SortFilesFirst:
+		slices.SortFunc(dents, func(d1, d2 DirEntry) int {
+			r1 := d1.Type().IsRegular()
+			r2 := d2.Type().IsRegular()
+			switch {
+			case r1 && !r2:
+				return -1
+			case !r1 && r2:
+				return 1
+			case !r1 && !r2:
+				// Both are not regular files: sort directories last
+				dd1 := d1.Type().IsDir()
+				dd2 := d2.Type().IsDir()
+				switch {
+				case !dd1 && dd2:
+					return -1
+				case dd1 && !dd2:
+					return 1
+				}
+			}
+			return strings.Compare(d1.Name(), d2.Name())
+		})
+	case SortDirsFirst:
+		slices.SortFunc(dents, func(d1, d2 DirEntry) int {
+			dd1 := d1.Type().IsDir()
+			dd2 := d2.Type().IsDir()
+			switch {
+			case dd1 && !dd2:
+				return -1
+			case !dd1 && dd2:
+				return 1
+			case !dd1 && !dd2:
+				// Both are not directories: sort regular files first
+				r1 := d1.Type().IsRegular()
+				r2 := d2.Type().IsRegular()
+				switch {
+				case r1 && !r2:
+					return -1
+				case !r1 && r2:
+					return 1
+				}
+			}
+			return strings.Compare(d1.Name(), d2.Name())
+		})
+	}
+}

dirent_portable_test.go

@@ -0,0 +1,131 @@
+//go:build !darwin && !(aix || dragonfly || freebsd || (js && wasm) || linux || netbsd || openbsd || solaris)
+
+package fastwalk
+
+import (
+	"io/fs"
+	"math/rand"
+	"reflect"
+	"testing"
+	"time"
+)
+
+var _ DirEntry = dirEntry{}
+
+// Minimal DirEntry for testing
+type dirEntry struct {
+	name string
+	typ  fs.FileMode
+}
+
+func (de dirEntry) Name() string               { return de.name }
+func (de dirEntry) IsDir() bool                { return de.typ.IsDir() }
+func (de dirEntry) Type() fs.FileMode          { return de.typ.Type() }
+func (de dirEntry) Info() (fs.FileInfo, error) { panic("not implemented") }
+func (de dirEntry) Stat() (fs.FileInfo, error) { panic("not implemented") }
+
+func (de dirEntry) String() string {
+	return fs.FormatDirEntry(de)
+}
+
+// NB: this must be kept in sync with the
+// TestSortDirents in dirent_unix_test.go
+func TestSortDirents(t *testing.T) {
+	direntNames := func(dents []DirEntry) []string {
+		names := make([]string, len(dents))
+		for i, d := range dents {
+			names[i] = d.Name()
+		}
+		return names
+	}
+
+	t.Run("None", func(t *testing.T) {
+		dents := []DirEntry{
+			dirEntry{name: "b"},
+			dirEntry{name: "a"},
+			dirEntry{name: "d"},
+			dirEntry{name: "c"},
+		}
+		want := direntNames(dents)
+		sortDirents(SortNone, dents)
+		got := direntNames(dents)
+		if !reflect.DeepEqual(got, want) {
+			t.Errorf("got: %q want: %q", got, want)
+		}
+	})
+
+	rr := rand.New(rand.NewSource(time.Now().UnixNano()))
+	shuffleDirents := func(dents []DirEntry) []DirEntry {
+		rr.Shuffle(len(dents), func(i, j int) {
+			dents[i], dents[j] = dents[j], dents[i]
+		})
+		return dents
+	}
+
+	// dents needs to be in the expected order
+	test := func(t *testing.T, dents []DirEntry, mode SortMode) {
+		want := direntNames(dents)
+		// Run multiple times with different shuffles
+		for i := 0; i < 10; i++ {
+			t.Run("", func(t *testing.T) {
+				sortDirents(mode, shuffleDirents(dents))
+				got := direntNames(dents)
+				if !reflect.DeepEqual(got, want) {
+					t.Errorf("got: %q want: %q", got, want)
+				}
+			})
+		}
+	}
+
+	t.Run("Lexical", func(t *testing.T) {
+		dents := []DirEntry{
+			dirEntry{name: "a"},
+			dirEntry{name: "b"},
+			dirEntry{name: "c"},
+			dirEntry{name: "d"},
+		}
+		test(t, dents, SortLexical)
+	})
+
+	t.Run("FilesFirst", func(t *testing.T) {
+		dents := []DirEntry{
+			// Files lexically
+			dirEntry{name: "f1", typ: 0},
+			dirEntry{name: "f2", typ: 0},
+			dirEntry{name: "f3", typ: 0},
+			// Non-dirs lexically
+			dirEntry{name: "a1", typ: fs.ModeSymlink},
+			dirEntry{name: "a2", typ: fs.ModeSymlink},
+			dirEntry{name: "a3", typ: fs.ModeSymlink},
+			dirEntry{name: "s1", typ: fs.ModeSocket},
+			dirEntry{name: "s2", typ: fs.ModeSocket},
+			dirEntry{name: "s3", typ: fs.ModeSocket},
+			// Dirs lexically
+			dirEntry{name: "d1", typ: fs.ModeDir},
+			dirEntry{name: "d2", typ: fs.ModeDir},
+			dirEntry{name: "d3", typ: fs.ModeDir},
+		}
+		test(t, dents, SortFilesFirst)
+	})
+
+	t.Run("DirsFirst", func(t *testing.T) {
+		dents := []DirEntry{
+			// Dirs lexically
+			dirEntry{name: "d1", typ: fs.ModeDir},
+			dirEntry{name: "d2", typ: fs.ModeDir},
+			dirEntry{name: "d3", typ: fs.ModeDir},
+			// Files lexically
+			dirEntry{name: "f1", typ: 0},
+			dirEntry{name: "f2", typ: 0},
+			dirEntry{name: "f3", typ: 0},
+			// Non-dirs lexically
+			dirEntry{name: "a1", typ: fs.ModeSymlink},
+			dirEntry{name: "a2", typ: fs.ModeSymlink},
+			dirEntry{name: "a3", typ: fs.ModeSymlink},
+			dirEntry{name: "s1", typ: fs.ModeSocket},
+			dirEntry{name: "s2", typ: fs.ModeSocket},
+			dirEntry{name: "s3", typ: fs.ModeSocket},
+		}
+		test(t, dents, SortDirsFirst)
+	})
+}