archive/zip: fix handling of replacement rune in UTF8 check

The replacement rune is a valid rune and can appear as itself in valid UTF8
(it encodes as three bytes). To check for invalid UTF8 it is necessary to
look for utf8.DecodeRune returning the replacement rune and size==1.

Change-Id: I169be8d1fe61605c921ac13cc2fde94f80f3463c
Reviewed-on: https://go-review.googlesource.com/78126
Run-TryBot: Russ Cox <[email protected]>
Reviewed-by: Joe Tsai <[email protected]>

Author: rsc

src/archive/zip/writer.go

@@ -219,15 +219,17 @@ func (w *Writer) Create(name string) (io.Writer, error) {
 // must be considered UTF-8 encoding (i.e., not compatible with CP-437, ASCII,
 // or any other common encoding).
 func detectUTF8(s string) (valid, require bool) {
-	for _, r := range s {
+	for i := 0; i < len(s); {
+		r, size := utf8.DecodeRuneInString(s[i:])
+		i += size
 		// Officially, ZIP uses CP-437, but many readers use the system's
 		// local character encoding. Most encoding are compatible with a large
 		// subset of CP-437, which itself is ASCII-like.
 		//
 		// Forbid 0x7e and 0x5c since EUC-KR and Shift-JIS replace those
 		// characters with localized currency and overline characters.
 		if r < 0x20 || r > 0x7d || r == 0x5c {
-			if !utf8.ValidRune(r) || r == utf8.RuneError {
+			if !utf8.ValidRune(r) || (r == utf8.RuneError && size == 1) {
 				return false, false
 			}
 			require = true

src/archive/zip/writer_test.go

@@ -136,40 +136,45 @@ func TestWriterUTF8(t *testing.T) {
 	var utf8Tests = []struct {
 		name    string
 		comment string
-		expect  uint16
 		nonUTF8 bool
+		flags   uint16
 	}{
 		{
 			name:    "hi, hello",
 			comment: "in the world",
-			expect:  0x8,
+			flags:   0x8,
 		},
 		{
 			name:    "hi, こんにちわ",
 			comment: "in the world",
-			expect:  0x808,
+			flags:   0x808,
 		},
 		{
 			name:    "hi, こんにちわ",
 			comment: "in the world",
 			nonUTF8: true,
-			expect:  0x8,
+			flags:   0x8,
 		},
 		{
 			name:    "hi, hello",
 			comment: "in the 世界",
-			expect:  0x808,
+			flags:   0x808,
 		},
 		{
 			name:    "hi, こんにちわ",
 			comment: "in the 世界",
-			expect:  0x808,
+			flags:   0x808,
+		},
+		{
+			name:    "the replacement rune is �",
+			comment: "the replacement rune is �",
+			flags:   0x808,
 		},
 		{
 			// Name is Japanese encoded in Shift JIS.
 			name:    "\x93\xfa\x96{\x8c\xea.txt",
 			comment: "in the 世界",
-			expect:  0x008, // UTF-8 must not be set
+			flags:   0x008, // UTF-8 must not be set
 		},
 	}
 
@@ -201,10 +206,9 @@ func TestWriterUTF8(t *testing.T) {
 		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)
+		flags := r.File[i].Flags
+		if flags != test.flags {
+			t.Errorf("CreateHeader(name=%q comment=%q nonUTF8=%v): flags=%#x, want %#x", test.name, test.comment, test.nonUTF8, flags, test.flags)
 		}
 	}
 }