zip: Merge upstream (#631)

* zip: Merge upstream

Add Go 1.19 improvements.

zip/fuzz_test.go

@@ -0,0 +1,84 @@
+//go:build go1.18
+// +build go1.18
+
+// Copyright 2021 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package zip
+
+import (
+	"bytes"
+	"io"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func FuzzReader(f *testing.F) {
+	testdata, err := os.ReadDir("testdata")
+	if err != nil {
+		f.Fatalf("failed to read testdata directory: %s", err)
+	}
+	for _, de := range testdata {
+		if de.IsDir() {
+			continue
+		}
+		b, err := os.ReadFile(filepath.Join("testdata", de.Name()))
+		if err != nil {
+			f.Fatalf("failed to read testdata: %s", err)
+		}
+		f.Add(b)
+	}
+
+	f.Fuzz(func(t *testing.T, b []byte) {
+		r, err := NewReader(bytes.NewReader(b), int64(len(b)))
+		if err != nil {
+			return
+		}
+
+		type file struct {
+			header  *FileHeader
+			content []byte
+		}
+		files := []file{}
+
+		for _, f := range r.File {
+			fr, err := f.Open()
+			if err != nil {
+				continue
+			}
+			content, err := io.ReadAll(fr)
+			if err != nil {
+				continue
+			}
+			files = append(files, file{header: &f.FileHeader, content: content})
+			if _, err := r.Open(f.Name); err != nil {
+				continue
+			}
+		}
+
+		// If we were unable to read anything out of the archive don't
+		// bother trying to roundtrip it.
+		if len(files) == 0 {
+			return
+		}
+
+		w := NewWriter(io.Discard)
+		for _, f := range files {
+			ww, err := w.CreateHeader(f.header)
+			if err != nil {
+				t.Fatalf("unable to write previously parsed header: %s", err)
+			}
+			if _, err := ww.Write(f.content); err != nil {
+				t.Fatalf("unable to write previously parsed content: %s", err)
+			}
+		}
+
+		if err := w.Close(); err != nil {
+			t.Fatalf("Unable to write archive: %s", err)
+		}
+
+		// TODO: We may want to check if the archive roundtrips.
+	})
+}

zip/reader.go

@@ -33,6 +33,10 @@ type Reader struct {
 	Comment       string
 	decompressors map[uint16]Decompressor
 
+	// Some JAR files are zip files with a prefix that is a bash script.
+	// The baseOffset field is the start of the zip file proper.
+	baseOffset int64
+
 	// fileList is a list of files sorted by ename,
 	// for use by the Open method.
 	fileListOnce sync.Once
@@ -52,9 +56,8 @@ type File struct {
 	FileHeader
 	zip          *Reader
 	zipr         io.ReaderAt
-	headerOffset int64
+	headerOffset int64 // includes overall ZIP archive baseOffset
 	zip64        bool  // zip64 extended information extra field presence
-	descErr      error // error reading the data descriptor during init
 }
 
 // OpenReader will open the Zip file specified by name and return a ReadCloser.
@@ -91,23 +94,24 @@ func NewReader(r io.ReaderAt, size int64) (*Reader, error) {
 }
 
 func (z *Reader) init(r io.ReaderAt, size int64) error {
-	end, err := readDirectoryEnd(r, size)
+	end, baseOffset, err := readDirectoryEnd(r, size)
 	if err != nil {
 		return err
 	}
 	z.r = r
+	z.baseOffset = baseOffset
 	// Since the number of directory records is not validated, it is not
 	// safe to preallocate z.File without first checking that the specified
 	// number of files is reasonable, since a malformed archive may
 	// indicate it contains up to 1 << 128 - 1 files. Since each file has a
 	// header which will be _at least_ 30 bytes we can safely preallocate
 	// if (data size / 30) >= end.directoryRecords.
-	if (uint64(size)-end.directorySize)/30 >= end.directoryRecords {
+	if end.directorySize < uint64(size) && (uint64(size)-end.directorySize)/30 >= end.directoryRecords {
 		z.File = make([]*File, 0, end.directoryRecords)
 	}
 	z.Comment = end.comment
 	rs := io.NewSectionReader(r, 0, size)
-	if _, err = rs.Seek(int64(end.directoryOffset), io.SeekStart); err != nil {
+	if _, err = rs.Seek(z.baseOffset+int64(end.directoryOffset), io.SeekStart); err != nil {
 		return err
 	}
 	buf := bufio.NewReader(rs)
@@ -119,12 +123,27 @@ func (z *Reader) init(r io.ReaderAt, size int64) error {
 	for {
 		f := &File{zip: z, zipr: r}
 		err = readDirectoryHeader(f, buf)
+
+		// For compatibility with other zip programs,
+		// if we have a non-zero base offset and can't read
+		// the first directory header, try again with a zero
+		// base offset.
+		if err == ErrFormat && z.baseOffset != 0 && len(z.File) == 0 {
+			z.baseOffset = 0
+			if _, err = rs.Seek(int64(end.directoryOffset), io.SeekStart); err != nil {
+				return err
+			}
+			buf.Reset(rs)
+			continue
+		}
+
 		if err == ErrFormat || err == io.ErrUnexpectedEOF {
 			break
 		}
 		if err != nil {
 			return err
 		}
+		f.headerOffset += z.baseOffset
 		z.File = append(z.File, f)
 	}
 	if uint16(len(z.File)) != uint16(end.directoryRecords) { // only compare 16 bits here
@@ -229,6 +248,9 @@ func (r *checksumReader) Read(b []byte) (n int, err error) {
 	n, err = r.rc.Read(b)
 	r.hash.Write(b[:n])
 	r.nread += uint64(n)
+	if r.nread > r.f.UncompressedSize64 {
+		return 0, ErrFormat
+	}
 	if err == nil {
 		return
 	}
@@ -492,7 +514,7 @@ func readDataDescriptor(r io.Reader, f *File) error {
 	return nil
 }
 
-func readDirectoryEnd(r io.ReaderAt, size int64) (dir *directoryEnd, err error) {
+func readDirectoryEnd(r io.ReaderAt, size int64) (dir *directoryEnd, baseOffset int64, err error) {
 	// look for directoryEndSignature in the last 1k, then in the last 65k
 	var buf []byte
 	var directoryEndOffset int64
@@ -502,15 +524,15 @@ func readDirectoryEnd(r io.ReaderAt, size int64) (dir *directoryEnd, err error)
 		}
 		buf = make([]byte, int(bLen))
 		if _, err := r.ReadAt(buf, size-bLen); err != nil && err != io.EOF {
-			return nil, err
+			return nil, 0, err
 		}
 		if p := findSignatureInBlock(buf); p >= 0 {
 			buf = buf[p:]
 			directoryEndOffset = size - bLen + int64(p)
 			break
 		}
 		if i == 1 || bLen == size {
-			return nil, ErrFormat
+			return nil, 0, ErrFormat
 		}
 	}
 
@@ -527,25 +549,29 @@ func readDirectoryEnd(r io.ReaderAt, size int64) (dir *directoryEnd, err error)
 	}
 	l := int(d.commentLen)
 	if l > len(b) {
-		return nil, errors.New("zip: invalid comment length")
+		return nil, 0, errors.New("zip: invalid comment length")
 	}
 	d.comment = string(b[:l])
 
 	// These values mean that the file can be a zip64 file
 	if d.directoryRecords == 0xffff || d.directorySize == 0xffff || d.directoryOffset == 0xffffffff {
 		p, err := findDirectory64End(r, directoryEndOffset)
 		if err == nil && p >= 0 {
+			directoryEndOffset = p
 			err = readDirectory64End(r, p, d)
 		}
 		if err != nil {
-			return nil, err
+			return nil, 0, err
 		}
 	}
+
+	baseOffset = directoryEndOffset - int64(d.directorySize) - int64(d.directoryOffset)
+
 	// Make sure directoryOffset points to somewhere in our file.
-	if o := int64(d.directoryOffset); o < 0 || o >= size {
-		return nil, ErrFormat
+	if o := baseOffset + int64(d.directoryOffset); o < 0 || o >= size {
+		return nil, 0, ErrFormat
 	}
-	return d, nil
+	return d, baseOffset, nil
 }
 
 // findDirectory64End tries to read the zip64 locator just before the
@@ -650,18 +676,22 @@ type fileListEntry struct {
 	name  string
 	file  *File
 	isDir bool
+	isDup bool
 }
 
 type fileInfoDirEntry interface {
 	fs.FileInfo
 	fs.DirEntry
 }
 
-func (e *fileListEntry) stat() fileInfoDirEntry {
+func (e *fileListEntry) stat() (fileInfoDirEntry, error) {
+	if e.isDup {
+		return nil, errors.New(e.name + ": duplicate entries in zip file")
+	}
 	if !e.isDir {
-		return headerFileInfo{&e.file.FileHeader}
+		return headerFileInfo{&e.file.FileHeader}, nil
 	}
-	return e
+	return e, nil
 }
 
 // Only used for directories.
@@ -696,32 +726,61 @@ func toValidName(name string) string {
 
 func (r *Reader) initFileList() {
 	r.fileListOnce.Do(func() {
+		// files and knownDirs map from a file/directory name
+		// to an index into the r.fileList entry that we are
+		// building. They are used to mark duplicate entries.
+		files := make(map[string]int)
+		knownDirs := make(map[string]int)
+
+		// dirs[name] is true if name is known to be a directory,
+		// because it appears as a prefix in a path.
 		dirs := make(map[string]bool)
-		knownDirs := make(map[string]bool)
+
 		for _, file := range r.File {
 			isDir := len(file.Name) > 0 && file.Name[len(file.Name)-1] == '/'
 			name := toValidName(file.Name)
+			if name == "" {
+				continue
+			}
+
+			if idx, ok := files[name]; ok {
+				r.fileList[idx].isDup = true
+				continue
+			}
+			if idx, ok := knownDirs[name]; ok {
+				r.fileList[idx].isDup = true
+				continue
+			}
+
 			for dir := path.Dir(name); dir != "."; dir = path.Dir(dir) {
 				dirs[dir] = true
 			}
+
+			idx := len(r.fileList)
 			entry := fileListEntry{
 				name:  name,
 				file:  file,
 				isDir: isDir,
 			}
 			r.fileList = append(r.fileList, entry)
 			if isDir {
-				knownDirs[name] = true
+				knownDirs[name] = idx
+			} else {
+				files[name] = idx
 			}
 		}
 		for dir := range dirs {
-			if !knownDirs[dir] {
-				entry := fileListEntry{
-					name:  dir,
-					file:  nil,
-					isDir: true,
+			if _, ok := knownDirs[dir]; !ok {
+				if idx, ok := files[dir]; ok {
+					r.fileList[idx].isDup = true
+				} else {
+					entry := fileListEntry{
+						name:  dir,
+						file:  nil,
+						isDir: true,
+					}
+					r.fileList = append(r.fileList, entry)
 				}
-				r.fileList = append(r.fileList, entry)
 			}
 		}
 
@@ -740,12 +799,11 @@ func fileEntryLess(x, y string) bool {
 // paths are always slash separated, with no
 // leading / or ../ elements.
 func (r *Reader) Open(name string) (fs.File, error) {
+	r.initFileList()
+
 	if !fs.ValidPath(name) {
 		return nil, &fs.PathError{Op: "open", Path: name, Err: fs.ErrInvalid}
 	}
-
-	r.initFileList()
-
 	e := r.openLookup(name)
 	if e == nil {
 		return nil, &fs.PathError{Op: "open", Path: name, Err: fs.ErrNotExist}
@@ -761,7 +819,7 @@ func (r *Reader) Open(name string) (fs.File, error) {
 }
 
 func split(name string) (dir, elem string, isDir bool) {
-	if name[len(name)-1] == '/' {
+	if len(name) > 0 && name[len(name)-1] == '/' {
 		isDir = true
 		name = name[:len(name)-1]
 	}
@@ -817,7 +875,7 @@ type openDir struct {
 }
 
 func (d *openDir) Close() error               { return nil }
-func (d *openDir) Stat() (fs.FileInfo, error) { return d.e.stat(), nil }
+func (d *openDir) Stat() (fs.FileInfo, error) { return d.e.stat() }
 
 func (d *openDir) Read([]byte) (int, error) {
 	return 0, &fs.PathError{Op: "read", Path: d.e.name, Err: errors.New("is a directory")}
@@ -836,7 +894,11 @@ func (d *openDir) ReadDir(count int) ([]fs.DirEntry, error) {
 	}
 	list := make([]fs.DirEntry, n)
 	for i := range list {
-		list[i] = d.files[d.offset+i].stat()
+		s, err := d.files[d.offset+i].stat()
+		if err != nil {
+			return nil, err
+		}
+		list[i] = s
 	}
 	d.offset += n
 	return list, nil