archive/squashfs: fix reading images with no fragment or xattr table

Bump go-diskfs to v1.9.4, which contains diskfs/go-diskfs#413 handling
squashfs images that have no fragment table or no xattr table. On v1.9.3
these images fail to list at all (ReadDir errors, or a nil xattr-table
dereference inside the library).

Adapt the backend to the v1.9.4 io/fs API: ReadDir now returns
io/fs.DirEntry (metadata via DirEntry.Info), and files are opened via
FileSystem.OpenFile instead of the removed FileStat.Open. The path
conversion added in c10eb47 (toIOFS) is reused.

Add a regression test with two committed fixtures built from trivial
placeholder content: an empty directory (no fragment table) and a small
tree whose superblock has the NO_XATTRS flag set while inodes still carry
an xattr index.

Fixes #9004

backend/archive/archive_internal_test.go

@@ -6,6 +6,7 @@ import (
 	"bytes"
 	"context"
 	"fmt"
+	"io"
 	"os"
 	"os/exec"
 	"path"
@@ -219,3 +220,60 @@ func TestArchiveSquashfs(t *testing.T) {
 		run(t, "mksquashfs", input, output)
 	})
 }
+
+// TestArchiveSquashfsIssue9004 lists and reads squashfs images that exercise
+// two layouts go-diskfs used to choke on (fixed in go-diskfs v1.9.4):
+//
+//   - 1.sqfs: a single empty directory, so the image has no fragment table
+//     (its fragment-table start holds the "not present" sentinel).
+//   - 2.sqfs: a small tree whose superblock has the NO_XATTRS flag set while
+//     inodes still carry a (non-sentinel) xattr index - the shape squashfs-
+//     tools-ng can emit. Built by packing a two-file tree with xattrs via
+//     `gensquashfs -x`, then setting the NO_XATTRS superblock flag; the tree
+//     content is trivial placeholder data.
+//
+// Both images used to fail to list. Regression test for #9004.
+func TestArchiveSquashfsIssue9004(t *testing.T) {
+	fstest.Initialise()
+	ctx := context.Background()
+
+	testdata, err := filepath.Abs(filepath.Join("squashfs", "testdata"))
+	require.NoError(t, err)
+
+	archiveFor := func(t *testing.T, name string) fs.Fs {
+		f, err := cache.Get(ctx, ":archive:"+filepath.Join(testdata, name))
+		require.NoError(t, err)
+		return f
+	}
+
+	t.Run("EmptyDir", func(t *testing.T) {
+		// 1.sqfs is a single empty directory - it must list without error.
+		entries, err := archiveFor(t, "1.sqfs").List(ctx, "")
+		require.NoError(t, err)
+		assert.Equal(t, 0, len(entries))
+	})
+
+	t.Run("NoXattrTree", func(t *testing.T) {
+		f := archiveFor(t, "2.sqfs")
+		entries, err := f.List(ctx, "")
+		require.NoError(t, err)
+		names := make([]string, 0, len(entries))
+		for _, e := range entries {
+			names = append(names, path.Base(e.Remote()))
+		}
+		assert.Contains(t, names, "alpha")
+		assert.Contains(t, names, "beta")
+
+		// A file in the tree must be readable with its real content.
+		obj, err := f.NewObject(ctx, "beta/sample.xml")
+		require.NoError(t, err)
+		assert.Greater(t, obj.Size(), int64(0))
+		rc, err := obj.Open(ctx)
+		require.NoError(t, err)
+		data, err := io.ReadAll(rc)
+		require.NoError(t, err)
+		require.NoError(t, rc.Close())
+		assert.Equal(t, int(obj.Size()), len(data))
+		assert.True(t, bytes.HasPrefix(data, []byte("<?xml")))
+	})
+}

backend/archive/squashfs/squashfs.go

@@ -5,6 +5,7 @@ import (
 	"context"
 	"fmt"
 	"io"
+	"os"
 	"path"
 	"strings"
 	"time"
@@ -180,13 +181,12 @@ func (f *Fs) fromNative(nativeDir string, leaf string) string {
 }
 
 // Convert a FileInfo into an Object from native dir
-func (f *Fs) objectFromFileInfo(nativeDir string, item squashfs.FileStat) *Object {
+func (f *Fs) objectFromFileInfo(nativeDir string, item os.FileInfo) *Object {
 	return &Object{
 		fs:      f,
 		remote:  f.fromNative(nativeDir, item.Name()),
 		size:    item.Size(),
 		modTime: item.ModTime(),
-		item:    item,
 	}
 }
 
@@ -213,26 +213,25 @@ func (f *Fs) List(ctx context.Context, dir string) (entries fs.DirEntries, err e
 	}
 
 	entries = make(fs.DirEntries, 0, len(items))
-	for _, fi := range items {
+	for _, item := range items {
-		item, ok := fi.(squashfs.FileStat)
-		if !ok {
-			return nil, fmt.Errorf("internal error: unexpected type for %q: %T", fi.Name(), fi)
-		}
 		// fs.Debugf(item.Name(), "entry = %#v", item)
 		var entry fs.DirEntry
-		if err != nil {
-			return nil, fmt.Errorf("error reading item %q: %q", item.Name(), err)
-		}
 		if item.IsDir() {
-			var remote = f.fromNative(nativeDir, item.Name())
+			remote := f.fromNative(nativeDir, item.Name())
-			entry = fs.NewDir(remote, item.ModTime())
+			info, err := item.Info()
-		} else {
+			if err != nil {
-			if item.Mode().IsRegular() {
+				return nil, fmt.Errorf("error reading item %q: %w", item.Name(), err)
-				entry = f.objectFromFileInfo(nativeDir, item)
-			} else {
-				fs.Debugf(item.Name(), "FIXME Not regular file - skipping")
-				continue
 			}
+			entry = fs.NewDir(remote, info.ModTime())
+		} else if item.Type().IsRegular() {
+			info, err := item.Info()
+			if err != nil {
+				return nil, fmt.Errorf("error reading item %q: %w", item.Name(), err)
+			}
+			entry = f.objectFromFileInfo(nativeDir, info)
+		} else {
+			fs.Debugf(item.Name(), "FIXME Not regular file - skipping")
+			continue
 		}
 		entries = append(entries, entry)
 	}
@@ -260,11 +259,11 @@ func (f *Fs) newObjectNative(nativePath string) (o fs.Object, err error) {
 			if fi.IsDir() {
 				return nil, fs.ErrorNotAFile
 			}
-			item, ok := fi.(squashfs.FileStat)
+			info, err := fi.Info()
-			if !ok {
+			if err != nil {
-				return nil, fmt.Errorf("internal error: unexpected type for %q: %T", fi.Name(), fi)
+				return nil, fmt.Errorf("error reading item %q: %w", fi.Name(), err)
 			}
-			o = f.objectFromFileInfo(dir, item)
+			o = f.objectFromFileInfo(dir, info)
 			break
 		}
 	}
@@ -339,7 +338,6 @@ type Object struct {
 	remote  string
 	size    int64
 	modTime time.Time
-	item    squashfs.FileStat
 }
 
 // Fs returns read only access to the Fs that this object is part of
@@ -416,8 +414,7 @@ func (o *Object) Open(ctx context.Context, options ...fs.OpenOption) (rc io.Read
 	}
 
 	fs.Debugf(o, "Opening %q", remote)
-	//fh, err := o.fs.sqfs.OpenFile(remote, os.O_RDONLY)
+	fh, err := o.fs.sqfs.OpenFile(toIOFS(remote), os.O_RDONLY)
-	fh, err := o.item.Open()
 	if err != nil {
 		return nil, err
 	}

go.mod

@@ -35,7 +35,7 @@ require (
 	github.com/colinmarc/hdfs/v2 v2.4.0
 	github.com/coreos/go-semver v0.3.1
 	github.com/coreos/go-systemd/v22 v22.6.0 // v22.7.0 fails to compile on netbsd - don't upgrade until fixed upstream
-	github.com/diskfs/go-diskfs v1.9.3
+	github.com/diskfs/go-diskfs v1.9.4
 	github.com/dop251/scsu v0.0.0-20220106150536-84ac88021d00
 	github.com/dropbox/dropbox-sdk-go-unofficial/v6 v6.4.0
 	github.com/gabriel-vasile/mimetype v1.4.13

go.sum

@@ -182,8 +182,8 @@ github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSs
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/diskfs/go-diskfs v1.9.3 h1:cLciNCeZ4QAXVxyPJDr1ZJ9N9CCG3rQlQ/z/Cs/cNDM=
+github.com/diskfs/go-diskfs v1.9.4 h1:0j2d7eG4IjyxL6+ChWbDPocdBCF6HQ4HBWU2WDYWVnc=
-github.com/diskfs/go-diskfs v1.9.3/go.mod h1:TePJORO83Adh5pb2SqsxAwaP0fofFxKLkxctiS/9OQc=
+github.com/diskfs/go-diskfs v1.9.4/go.mod h1:TePJORO83Adh5pb2SqsxAwaP0fofFxKLkxctiS/9OQc=
 github.com/djherbis/times v1.6.0 h1:w2ctJ92J8fBvWPxugmXIv7Nz7Q3iDMKNx9v5ocVH20c=
 github.com/djherbis/times v1.6.0/go.mod h1:gOHeRAz2h+VJNZ5Gmc/o7iD9k4wW7NMVqieYCY99oc0=
 github.com/dnaeon/go-vcr v1.2.0 h1:zHCHvJYTMh1N7xnV7zf1m1GPBF9Ad0Jk/whtQ1663qI=