archive/zip: set utf-8 flag

See: https://pkware.cachefly.net/webdocs/APPNOTE/APPNOTE-6.3.0.TXT

Document says:
> If general purpose bit 11 is set, the filename and comment must support The
> Unicode Standard, Version 4.1.0 or greater using the character encoding form
> defined by the UTF-8 storage specification.

Since Go encode the filename to UTF-8, general purpose bit 11 should be set.

Change-Id: Ica4af02b4dc695e9a5c015ae360e70171efb6ee3
Reviewed-on: https://go-review.googlesource.com/39570
Reviewed-by: Joe Tsai <[email protected]>
Run-TryBot: Joe Tsai <[email protected]>
TryBot-Result: Gobot Gobot <[email protected]>

Author: mattn

src/archive/zip/writer.go

@@ -11,6 +11,7 @@ import (
 	"hash"
 	"hash/crc32"
 	"io"
+	"unicode/utf8"
 )
 
 // TODO(adg): support zip file comments
@@ -201,6 +202,20 @@ func (w *Writer) Create(name string) (io.Writer, error) {
 	return w.CreateHeader(header)
 }
 
+func hasValidUTF8(s string) bool {
+	n := 0
+	for _, r := range s {
+		// By default, ZIP uses CP437, which is only identical to ASCII for the printable characters.
+		if r < 0x20 || r >= 0x7f {
+			if !utf8.ValidRune(r) {
+				return false
+			}
+			n++
+		}
+	}
+	return n > 0
+}
+
 // CreateHeader adds a file to the zip file using the provided FileHeader
 // for the file metadata.
 // It returns a Writer to which the file contents should be written.
@@ -221,6 +236,10 @@ func (w *Writer) CreateHeader(fh *FileHeader) (io.Writer, error) {
 
 	fh.Flags |= 0x8 // we will write a data descriptor
 
+	if hasValidUTF8(fh.Name) || hasValidUTF8(fh.Comment) {
+		fh.Flags |= 0x800 // filename or comment have valid utf-8 string
+	}
+
 	fh.CreatorVersion = fh.CreatorVersion&0xff00 | zipVersion20 // preserve compatibility byte
 	fh.ReaderVersion = zipVersion20
 

src/archive/zip/writer_test.go

@@ -87,6 +87,69 @@ func TestWriter(t *testing.T) {
 	}
 }
 
+func TestWriterUTF8(t *testing.T) {
+	var utf8Tests = []struct {
+		name    string
+		comment string
+		expect  uint16
+	}{
+		{
+			name:    "hi, hello",
+			comment: "in the world",
+			expect:  0x8,
+		},
+		{
+			name:    "hi, こんにちわ",
+			comment: "in the world",
+			expect:  0x808,
+		},
+		{
+			name:    "hi, hello",
+			comment: "in the 世界",
+			expect:  0x808,
+		},
+		{
+			name:    "hi, こんにちわ",
+			comment: "in the 世界",
+			expect:  0x808,
+		},
+	}
+
+	// write a zip file
+	buf := new(bytes.Buffer)
+	w := NewWriter(buf)
+
+	for _, test := range utf8Tests {
+		h := &FileHeader{
+			Name:    test.name,
+			Comment: test.comment,
+			Method:  Deflate,
+		}
+		w, err := w.CreateHeader(h)
+		if err != nil {
+			t.Fatal(err)
+		}
+		w.Write([]byte{})
+	}
+
+	if err := w.Close(); err != nil {
+		t.Fatal(err)
+	}
+
+	// read it back
+	r, err := NewReader(bytes.NewReader(buf.Bytes()), int64(buf.Len()))
+	if err != nil {
+		t.Fatal(err)
+	}
+	for i, test := range utf8Tests {
+		got := r.File[i].Flags
+		t.Logf("name %v, comment %v", test.name, test.comment)
+		if got != test.expect {
+			t.Fatalf("Flags: got %v, want %v", got, test.expect)
+		}
+	}
+}
+
 func TestWriterOffset(t *testing.T) {
 	largeData := make([]byte, 1<<17)
 	for i := range largeData {