strings: fix handling of invalid UTF-8 sequences in Map

The new Map implementation introduced in golang.org/cl/33201
did not differentiate if an invalid UTF-8 sequence was decoded
or the RuneError rune. It would therefore always advance by
3 bytes (which is the length of the RuneError rune) instead
of 1 for an invalid sequences. This cl adds a check to correctly
determine the length of bytes needed to advance to the next rune.

Fixes #19330.

Change-Id: I1e7f9333f3ef6068ffc64015bb0a9f32b0b7111d
Reviewed-on: https://go-review.googlesource.com/37597
Run-TryBot: Martin Möhrmann <moehrmann@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Joe Tsai <thebrokentoaster@gmail.com>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>

src/strings/strings.go

@@ -406,7 +406,17 @@ func Map(mapping func(rune) rune, s string) string {
 				nbytes += utf8.EncodeRune(b[nbytes:], r)
 			}
 		}
-		i += utf8.RuneLen(c)
+
+		if c == utf8.RuneError {
+			// RuneError is the result of either decoding
+			// an invalid sequence or '\uFFFD'. Determine
+			// the correct number of bytes we need to advance.
+			_, w := utf8.DecodeRuneInString(s[i:])
+			i += w
+		} else {
+			i += utf8.RuneLen(c)
+		}
+
 		s = s[i:]
 		break
 	}

src/strings/strings_test.go

@@ -625,6 +625,19 @@ func TestMap(t *testing.T) {
 		(*reflect.StringHeader)(unsafe.Pointer(&m)).Data {
 		t.Error("unexpected copy during identity map")
 	}
+
+	// 7. Handle invalid UTF-8 sequence
+	replaceNotLatin := func(r rune) rune {
+		if unicode.Is(unicode.Latin, r) {
+			return r
+		}
+		return '?'
+	}
+	m = Map(replaceNotLatin, "Hello\255World")
+	expect = "Hello?World"
+	if m != expect {
+		t.Errorf("replace invalid sequence: expected %q got %q", expect, m)
+	}
 }
 
 func TestToUpper(t *testing.T) { runStringTests(t, ToUpper, "ToUpper", upperTests) }