zip: support non-utf8 filenames

cmd/arc/main.go

@@ -21,6 +21,7 @@ var (
 	selectiveCompression   bool
 	implicitTopLevelFolder bool
 	continueOnError        bool
+	filenameEncoding       string
 )
 
 func init() {
@@ -30,6 +31,7 @@ func init() {
 	flag.BoolVar(&selectiveCompression, "smart", true, "Only compress files which are not already compressed (zip only)")
 	flag.BoolVar(&implicitTopLevelFolder, "folder-safe", true, "If an archive does not have a single top-level folder, create one implicitly")
 	flag.BoolVar(&continueOnError, "allow-errors", true, "Log errors and continue processing")
+	flag.StringVar(&filenameEncoding, "filename-encoding", "", "Specify encoding if filename was not utf8 encoded")
 }
 
 func main() {
@@ -229,6 +231,7 @@ func getFormat(subcommand string) (interface{}, error) {
 		v.SelectiveCompression = selectiveCompression
 		v.ImplicitTopLevelFolder = implicitTopLevelFolder
 		v.ContinueOnError = continueOnError
+		v.FilenameEncoding = filenameEncoding
 	case *archiver.Gz:
 		v.CompressionLevel = compressionLevel
 	case *archiver.Bz2:

encoding.go

@@ -0,0 +1,67 @@
+package archiver
+
+import (
+	"errors"
+	"strings"
+
+	"golang.org/x/text/encoding"
+	"golang.org/x/text/encoding/charmap"
+	"golang.org/x/text/encoding/japanese"
+	"golang.org/x/text/encoding/korean"
+	"golang.org/x/text/encoding/simplifiedchinese"
+	"golang.org/x/text/encoding/traditionalchinese"
+	"golang.org/x/text/encoding/unicode"
+)
+
+var encodings = map[string]encoding.Encoding{
+	"ibm866":            charmap.CodePage866,
+	"iso8859_2":         charmap.ISO8859_2,
+	"iso8859_3":         charmap.ISO8859_3,
+	"iso8859_4":         charmap.ISO8859_4,
+	"iso8859_5":         charmap.ISO8859_5,
+	"iso8859_6":         charmap.ISO8859_6,
+	"iso8859_7":         charmap.ISO8859_7,
+	"iso8859_8":         charmap.ISO8859_8,
+	"iso8859_8I":        charmap.ISO8859_8I,
+	"iso8859_10":        charmap.ISO8859_10,
+	"iso8859_13":        charmap.ISO8859_13,
+	"iso8859_14":        charmap.ISO8859_14,
+	"iso8859_15":        charmap.ISO8859_15,
+	"iso8859_16":        charmap.ISO8859_16,
+	"koi8r":             charmap.KOI8R,
+	"koi8u":             charmap.KOI8U,
+	"macintosh":         charmap.Macintosh,
+	"windows874":        charmap.Windows874,
+	"windows1250":       charmap.Windows1250,
+	"windows1251":       charmap.Windows1251,
+	"windows1252":       charmap.Windows1252,
+	"windows1253":       charmap.Windows1253,
+	"windows1254":       charmap.Windows1254,
+	"windows1255":       charmap.Windows1255,
+	"windows1256":       charmap.Windows1256,
+	"windows1257":       charmap.Windows1257,
+	"windows1258":       charmap.Windows1258,
+	"macintoshcyrillic": charmap.MacintoshCyrillic,
+	"gbk":               simplifiedchinese.GBK,
+	"gb18030":           simplifiedchinese.GB18030,
+	"big5":              traditionalchinese.Big5,
+	"eucjp":             japanese.EUCJP,
+	"iso2022jp":         japanese.ISO2022JP,
+	"shiftjis":          japanese.ShiftJIS,
+	"euckr":             korean.EUCKR,
+	"utf16be":           unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM),
+	"utf16le":           unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM),
+}
+
+func GetEncoding(charset string) (encoding.Encoding, bool) {
+	charset = strings.ToLower(charset)
+	enc, ok := encodings[charset]
+	return enc, ok
+}
+
+func Decode(in []byte, charset string) ([]byte, error) {
+	if enc, ok := GetEncoding(charset); ok {
+		return enc.NewDecoder().Bytes(in)
+	}
+	return nil, errors.New("charset not found!")
+}

zip.go

@@ -55,6 +55,10 @@ type Zip struct {
 	// the operation will continue on remaining files.
 	ContinueOnError bool
 
+	// If zip.FileHeader.NonUTF8 was true, this can be
+	// used to decode filename to utf8
+	FilenameEncoding string
+
 	zw   *zip.Writer
 	zr   *zip.Reader
 	ridx int
@@ -191,7 +195,8 @@ func (z *Zip) extractFile(f File, to string) error {
 		return fmt.Errorf("expected header to be zip.FileHeader but was %T", f.Header)
 	}
 
-	to = filepath.Join(to, header.Name)
+	filename := z.DecodeFileName(header)
+	to = filepath.Join(to, filename)
 
 	// if a directory, no content; simply make the directory and return
 	if f.IsDir() {
@@ -444,6 +449,8 @@ func (z *Zip) Walk(archive string, walkFn WalkFunc) error {
 			return fmt.Errorf("opening %s: %v", zf.Name, err)
 		}
 
+		zf.FileHeader.Name = z.DecodeFileName(zf.FileHeader)
+
 		err = walkFn(File{
 			FileInfo:   zf.FileInfo(),
 			Header:     zf.FileHeader,
@@ -483,6 +490,8 @@ func (z *Zip) Extract(source, target, destination string) error {
 			return fmt.Errorf("expected header to be zip.FileHeader but was %T", f.Header)
 		}
 
+		zfh.Name = z.DecodeFileName(zfh)
+
 		// importantly, cleaning the path strips tailing slash,
 		// which must be appended to folders within the archive
 		name := path.Clean(zfh.Name)
@@ -539,6 +548,15 @@ func (*Zip) Match(file io.ReadSeeker) (bool, error) {
 	return bytes.Equal(buf, []byte("PK\x03\x04")), nil
 }
 
+func (z *Zip) DecodeFileName(header zip.FileHeader) string {
+	if header.NonUTF8 && z.FilenameEncoding != "" {
+		if filename, err := Decode([]byte(header.Name), z.FilenameEncoding); err == nil {
+			return string(filename)
+		}
+	}
+	return header.Name
+}
+
 func (z *Zip) String() string { return "zip" }
 
 // NewZip returns a new, default instance ready to be customized and used.